[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MG8T1ZM1ZD3Z7CSD1TYS4B":3,"skill-same:01M6MG8T1ZM1ZD3Z7CSD1TYS4B":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6MG8T1ZM1ZD3Z7CSD1TYS4B","orbit",null,"State-persisted autonomous pipeline: spec → go → audit → eval → ship → evolve in one command. Auto-detects direct\u002Fcouncil\u002Finteractive mode. Crash-recoverable via PIPELINE-*.json. Hands-off until PR.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002Forbit\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"eval","mode","via","crash","auto","autonomous","interactive","command","evolve","spec","direct","json","ship","pipeline","audit","state","council","pr","go","2026-11-10 10:12:30",false,"---\nname: orbit\ndescription: \"State-persisted autonomous pipeline: spec → go → audit → eval → ship → evolve in one command. Auto-detects direct\u002Fcouncil\u002Finteractive mode. Crash-recoverable via PIPELINE-*.json. Hands-off until PR.\"\n---\n\n# \u002Forbit — Complete Orbit\n\n**CRITICAL**: Run `HARNESS_DIR=$(epic path)` first. NEVER use `.harness\u002F` in the project directory.\n\nYou are entering **Orbit** mode — the full autonomous pipeline from spec to PR in one shot.\n\n## Phase Recovery Protocol\n\nAt the start of **every response** during an active orbit:\n\n1. Run `ls $HARNESS_DIR\u002Forbit\u002FPIPELINE-*.json 2>\u002Fdev\u002Fnull`\n2. Find the file with `\"status\": \"running\"`\n3. Read it. Verify `phase` matches where you left off\n4. **If `phase` is ahead of where you think you are, trust the file** — you may have compacted\n5. **Conflict resolution (crash-mid-update)**: If `phase_history` contains an entry for the current `phase` with a completed timestamp, treat that phase as done and advance to the next phase — `phase_history` wins over the `phase` field when they disagree.\n6. Resume from the resolved phase. Do NOT re-ask mode selection, re-run spec, or re-discover\n7. **Worktree recovery**: If `worktree_name` is set in pipeline state:\n   - Check if worktree still exists: `git worktree list | grep \"{worktree_name}\"`\n   - If exists: `cd` into the worktree path to continue work\n   - If not found: worktree was cleaned up externally — abort orbit with warning, set `\"status\": \"aborted\"`\n\nIf no file with `\"status\": \"running\"` exists, orbit was not started or has completed. Do not invent one.\n\n**Crash recovery**: If `updated_at` is older than 45 minutes and the pipeline is in `status: running`, assume a crash occurred. Read the state, determine the last completed phase from `phase_history` (rule 5 above applies), and resume from there. Report the recovery to the user.\n\n## Step 0: Preflight\n\n**Concurrent-orbit guard** — before starting, run:\n\n```bash\nepic orbit lock   # exit 1 + \"another orbit is running\" if one is active → STOP\n```\n\nOn success you own the guard; run `epic orbit unlock` when the pipeline reaches\na terminal state (complete\u002Faborted). If a crashed orbit left the lock behind,\n`lock` reclaims it automatically once no PIPELINE-*.json is `running`.\n\nInitialize pipeline state at `$HARNESS_DIR\u002Forbit\u002FPIPELINE-{timestamp}.json`:\n```json\n{\n  \"id\": \"{timestamp}\",\n  \"mode\": null,\n  \"phase\": \"auto_detect\",\n  \"status\": \"running\",\n  \"spec_file\": null,\n  \"goal_slug\": null,\n  \"branch\": null,\n  \"worktree_name\": null,\n  \"original_cwd\": null,\n  \"audit_fail_count\": 0,\n  \"max_retries\": 3,\n  \"audit_report\": null,\n  \"pr_url\": null,\n  \"deadline\": \"{ISO-8601, now + 30 minutes}\",\n  \"started_at\": \"{ISO-8601}\",\n  \"updated_at\": \"{ISO-8601}\",\n  \"phase_history\": []\n}\n```\n\n## Step 1: Auto-Detect Mode\n\n**DO NOT ask the user for mode selection.** Auto-detect the best path:\n\n### Detection Logic\n\n| Signal | Mode | Reason |\n|--------|------|--------|\n| PRD \u002F detailed requirements doc exists in project | `council` | Rich input → council synthesizes best approach |\n| User request is specific and actionable (clear goal, defined scope) | `direct` | No need for discovery — spec directly |\n| User request is vague, unfocused, or \"I want to...\" without specifics | `council` | Council frames the problem better than guessing |\n| User explicitly says \"interactive\" or \"let me discover first\" | `interactive` | Respect explicit preference |\n\n### Detection Process\n\n1. Check for PRD\u002Frequirements docs: `ls {project}\u002FPRD*.md {project}\u002Fdocs\u002FPRD*.md {project}\u002Frequirements*.md 2>\u002Fdev\u002Fnull`\n2. Evaluate user request clarity:\n   - **Specific**: contains concrete feature descriptions, acceptance criteria, or technical constraints → `direct`\n   - **Vague**: \"build X\", \"improve Y\", \"add Z\" without details → `council`\n3. Record detected mode in pipeline state (`\"mode\": \"direct|council|interactive\"`)\n4. Report mode choice to user as a **notification**, not a question: `\"Orbit mode: {mode} (auto-detected)\"`\n5. Proceed immediately to the matching step below — **do not wait for confirmation**\n\n## Step 2A: Direct Mode (clear request → auto-spec)\n\n**Use when**: Request is specific and actionable.\n\n1. Read the user's request + any existing docs (PRD, README, AGENTS.md)\n2. Generate spec directly at `$HARNESS_DIR\u002Fspecs\u002FSPEC-{timestamp}.md`, run the **Readiness gate** from `skills\u002Fspec\u002FSKILL.md` (step 3) on it, settle every `GAP:` from the request and codebase yourself, record each as `GAP: … → settled: … (assumption)` under the spec's `## Readiness Gate`, then write `status: approved`. If a gap cannot be settled without the user, downgrade to `council` mode instead of guessing.\n3. Record via `epic mem add --title \"Orbit: {mode} mode decision\" --type decision --importance 0.9 --body \"CONTEXT\"`\n4. **Proceed immediately to Step 3** — no approval gate\n\n## Step 2B: Council Auto-Spec (complex\u002Fvague request → council)\n\n**Use when**: PRD exists or request needs framing.\n\n1. Gather the user's request from conversation context\n2. Launch 4 parallel sub-agents (Architect, Skeptic, Pragmatist, Critic) — each receives ONLY the request + codebase context, NOT the full conversation (anti-anchoring)\n3. Synthesize: list agreement\u002Fdisagreement, produce recommended approach\n4. Generate spec at `$HARNESS_DIR\u002Fspecs\u002FSPEC-{timestamp}.md`, run the **Readiness gate** (spec skill step 3), settle every `GAP:` from the council output and record each under `## Readiness Gate`, then write `status: approved`\n5. Record via `epic mem add --title \"Orbit: council decision\" --type decision --importance 0.9 --body \"CONTEXT\"`\n6. **Proceed immediately to Step 3** — no approval gate, no \"orbit go\"\n\n## Step 2C: Interactive Mode (explicit user choice only)\n\n**Use when**: User explicitly requested interactive mode.\n\n1. Tell user to run `\u002Fdiscover` → `\u002Fspec`, then say \"orbit go\". STOP and wait.\n2. On resume: load latest `SPEC-*.md` with `status: approved`. Proceed to Step 3.\n\n**This mode is never auto-selected.** It requires explicit user opt-in.\n\n## Step 3: Build (Go)\n\n1. Load spec, extract `goal_slug`\n2. **Git preflight**: verify clean working tree and not on detached HEAD:\n   ```bash\n   [ -z \"$(git status --porcelain)\" ] || (echo \"ERROR: Dirty working tree or untracked files. Commit or stash first.\" && exit 1)\n   git symbolic-ref -q HEAD || (echo \"ERROR: Detached HEAD. Checkout a branch first.\" && exit 1)\n   ```\n3. **Worktree isolation**: Create an isolated git worktree:\n   ```bash\n   git worktree add .harness\u002Fworktrees\u002Forbit-{goal_slug} -b orbit-{goal_slug} origin\u002F{default-branch}\n   cd .harness\u002Fworktrees\u002Forbit-{goal_slug}\n   ```\n   - `.harness\u002Fworktrees\u002F` is host-neutral. Do NOT use `.claude\u002Fworktrees\u002F` —\n     it is meaningless on Codex and Antigravity.\n   - Record `worktree_name` and `original_cwd` in pipeline state\n4. Plan tasks from Requirements (R1, R2...)\n5. Execute with sub-agents — TDD, debug on failure, verify before done\n6. Handle states: DONE \u002F DONE_WITH_CONCERNS \u002F NEEDS_CONTEXT \u002F BLOCKED\n7. Integrate: full test suite, verify ACs\n\n## Step 4: Audit\n\n1. Gather scope via `git diff --stat`\n2. Classify changed files (API, Frontend, DB, Backend, Tests, Infra)\n3. Launch parallel sub-agents: Reviewer, Auditor, Test runner (+ scope-specific)\n4. Synthesize Audit Report: Quality\u002FSecurity\u002FPerformance PASS\u002FWARN\u002FFAIL + Spec Coverage\n5. **PRESERVE audit report** in pipeline state `audit_report` field\n\n## Step 5: Verdict\n\n- **All PASS + all AC verified** → proceed to Eval (if eval.yaml exists) or Ship\n- **WARN** → log, auto-proceed\n- **FAIL** → increment `audit_fail_count`:\n  - `\u003C 3`: plan fixes from action items, execute, return to Step 4\n  - `≥ 3`: **PAUSE** — ask user \"continue or abort?\"\n\n## Step 5.5: Eval (optional — only if eval.yaml or benchmarks exist)\n\n1. Check for eval config — eval is active if ANY of these exist:\n   - `$HARNESS_DIR\u002Feval\u002Feval.yaml`\n   - `benchmarks\u002Fbaselines\u002Flatest.json` in CWD (in-repo baseline)\n   - `benchmarks\u002Feval_runner.py` in CWD (auto-detected benchmark)\n2. If eval is active, run `epic eval --json` via the **eval** skill\n3. **Eval PASS** → proceed to Ship\n4. **Eval FAIL (regression detected)** → increment `audit_fail_count`:\n   - `\u003C 3`: plan fixes, execute, return to Step 4\n   - `≥ 3`: **PAUSE** — ask user \"continue or abort?\"\n5. If no eval config and no benchmarks detected, skip this step entirely\n\n## Step 6: Ship\n\n1. **Gate**: verify PASS audit report exists\n2. **Integration verification** — run directly in worktree:\n   - Clean build artifacts first: `cargo clean` \u002F `npm run clean` \u002F equivalent\n   - Full build from scratch · complete test suite · linter + formatter\n   - Fail → STOP. Do NOT create PR.\n3. **Git hygiene**: conventional commits, rebase, squash fixups\n4. **Create PR** via `gh pr create` with spec + audit report in body\n   - Record the URL in pipeline state as `pr_url`. `epic orbit unlock` warns\n     when a pipeline reaches `complete` without it.\n5. **CI watch** — probe first, then watch:\n   ```bash\n   gh pr checks \u003CPR_NUMBER> --json name,state\n   ```\n   - Checks exist → run `gh pr checks \u003CPR_NUMBER> --watch`, auto-fix failures.\n   - Empty result (no CI configured on the repo) → **skip the watch**. Log\n     \"No CI configured, skipping CI watch\", append a `phase_history` entry\n     recording `\"ci_watch\": \"skipped\"`, and proceed to Step 7 (evolve runs\n     regardless of CI outcome, so the pipeline must never wait on checks\n     that will never appear).\n6. **Exit worktree**: Return to original directory and keep the worktree\n\n## Step 7: Evolve\n\nRun the evolution engine to analyze this session and generate\u002Fimprove skills.\n\n1. **Always run** — regardless of CI outcome:\n   ```bash\n   epic-harness reflect\n   ```\n   This triggers the Ring 3 loop: observe → analyze → seed evolved skills → update metrics.\n\n   If `$HARNESS_DIR\u002Fprojects\u002F{slug}\u002Fpending_synth.jsonl` has records with `status: \"pending\"`,\n   synthesize each — launch one subagent per manifest (use your host's subagent\n   mechanism; do NOT name a model or CLI), then apply the body it produced:\n   ```bash\n   epic-harness evolve accept-synth --skill \u003Cname> --file \u003Cbody.md>\n   ```\n   Unconsumed manifests leave the template skill body in place.\n\n2. **If CI green** (all checks passed): additionally run\n   ```bash\n   epic-harness reflect --context --days 1\n   ```\n   and record the successful orbit pattern into memory:\n   ```bash\n   epic mem add --title \"Orbit: {goal_slug} succeeded\" \\\n     --type pattern --importance 0.7 \\\n     --body \"Orbit completed. Mode: {mode}. AC: all verified. PR: {url}. Stack: {stack}.\"\n   ```\n\n3. Report the evolution outcome in the final summary (evolved skills generated, score trend).\n\n4. Update pipeline state: `\"phase\": \"evolve\"`, `\"status\": \"complete\"`, then run `epic orbit unlock`.\n\n## Step 8: Report\n\n```\n## Orbit Complete\n- Pipeline: PIPELINE-{id}\n- Mode: {direct|council|interactive} (auto-detected)\n- Spec: SPEC-{timestamp} ({goal_slug})\n- Branch: orbit-{goal_slug}\n- Worktree: orbit-{goal_slug} (preserved for PR)\n- PR: {URL}\n- Audit retries: {count}\n\n### Phase Summary\n| Phase | Status | Retries |\n|-------|--------|---------|\n| Spec | approved | 0 |\n| Go | complete | 0 |\n| Audit | PASS | {count} |\n| Eval | {PASS|SKIPPED} | 0 |\n| Ship | complete | 0 |\n| Evolve | complete | 0 |\n\n### Evolution\n- Skills evolved: {count}\n- Score trend: {improving|stable|declining}\n```\n\n## Red Flags\n- Interactive mode proceeding without spec approval (direct and council modes auto-approve)\n- Continuing after 3 audit failures without user consent\n- Skipping isolated integration test\n- Shipping with FAIL in security audits\n- Losing audit report between phases\n- Creating branch with dirty working tree\n- Losing worktree reference between phases\n- Skipping evolve step after ship (evolve must always run, even if CI fails)\n","# \u002Forbit — Complete Orbit\n\n**CRITICAL**: Run `HARNESS_DIR=$(epic path)` first. NEVER use `.harness\u002F` in the project directory.\n\nYou are entering **Orbit** mode — the full autonomous pipeline from spec to PR in one shot.\n\n## Phase Recovery Protocol\n\nAt the start of **every response** during an active orbit:\n\n1. Run `ls $HARNESS_DIR\u002Forbit\u002FPIPELINE-*.json 2>\u002Fdev\u002Fnull`\n2. Find the file with `\"status\": \"running\"`\n3. Read it. Verify `phase` matches where you left off\n4. **If `phase` is ahead of where you think you are, trust the file** — you may have compacted\n5. **Conflict resolution (crash-mid-update)**: If `phase_history` contains an entry for the current `phase` with a completed timestamp, treat that phase as done and advance to the next phase — `phase_history` wins over the `phase` field when they disagree.\n6. Resume from the resolved phase. Do NOT re-ask mode selection, re-run spec, or re-discover\n7. **Worktree recovery**: If `worktree_name` is set in pipeline state:\n   - Check if worktree still exists: `git worktree list | grep \"{worktree_name}\"`\n   - If exists: `cd` into the worktree path to continue work\n   - If not found: worktree was cleaned up externally — abort orbit with warning, set `\"status\": \"aborted\"`\n\nIf no file with `\"status\": \"running\"` exists, orbit was not started or has completed. Do not invent one.\n\n**Crash recovery**: If `updated_at` is older than 45 minutes and the pipeline is in `status: running`, assume a crash occurred. Read the state, determine the last completed phase from `phase_history` (rule 5 above applies), and resume from there. Report the recovery to the user.\n\n## Step 0: Preflight\n\n**Concurrent-orbit guard** — before starting, run:\n\n```bash\nepic orbit lock   # exit 1 + \"another orbit is running\" if one is active → STOP\n```\n\nOn success you own the guard; run `epic orbit unlock` when the pipeline reaches\na terminal state (complete\u002Faborted). If a crashed orbit left the lock behind,\n`lock` reclaims it automatically once no PIPELINE-*.json is `running`.\n\nInitialize pipeline state at `$HARNESS_DIR\u002Forbit\u002FPIPELINE-{timestamp}.json`:\n```json\n{\n  \"id\": \"{timestamp}\",\n  \"mode\": null,\n  \"phase\": \"auto_detect\",\n  \"status\": \"running\",\n  \"spec_file\": null,\n  \"goal_slug\": null,\n  \"branch\": null,\n  \"worktree_name\": null,\n  \"original_cwd\": null,\n  \"audit_fail_count\": 0,\n  \"max_retries\": 3,\n  \"audit_report\": null,\n  \"pr_url\": null,\n  \"deadline\": \"{ISO-8601, now + 30 minutes}\",\n  \"started_at\": \"{ISO-8601}\",\n  \"updated_at\": \"{ISO-8601}\",\n  \"phase_history\": []\n}\n```\n\n## Step 1: Auto-Detect Mode\n\n**DO NOT ask the user for mode selection.** Auto-detect the best path:\n\n### Detection Logic\n\n| Signal | Mode | Reason |\n|--------|------|--------|\n| PRD \u002F detailed requirements doc exists in project | `council` | Rich input → council synthesizes best approach |\n| User request is specific and actionable (clear goal, defined scope) | `direct` | No need for discovery — spec directly |\n| User request is vague, unfocused, or \"I want to...\" without specifics | `council` | Council frames the problem better than guessing |\n| User explicitly says \"interactive\" or \"let me discover first\" | `interactive` | Respect explicit preference |\n\n### Detection Process\n\n1. Check for PRD\u002Frequirements docs: `ls {project}\u002FPRD*.md {project}\u002Fdocs\u002FPRD*.md {project}\u002Frequirements*.md 2>\u002Fdev\u002Fnull`\n2. Evaluate user request clarity:\n   - **Specific**: contains concrete feature descriptions, acceptance criteria, or technical constraints → `direct`\n   - **Vague**: \"build X\", \"improve Y\", \"add Z\" without details → `council`\n3. Record detected mode in pipeline state (`\"mode\": \"direct|council|interactive\"`)\n4. Report mode choice to user as a **notification**, not a question: `\"Orbit mode: {mode} (auto-detected)\"`\n5. Proceed immediately to the matching step below — **do not wait for confirmation**\n\n## Step 2A: Direct Mode (clear request → auto-spec)\n\n**Use when**: Request is specific and actionable.\n\n1. Read the user's request + any existing docs (PRD, README, AGENTS.md)\n2. Generate spec directly at `$HARNESS_DIR\u002Fspecs\u002FSPEC-{timestamp}.md`, run the **Readiness gate** from `skills\u002Fspec\u002FSKILL.md` (step 3) on it, settle every `GAP:` from the request and codebase yourself, record each as `GAP: … → settled: … (assumption)` under the spec's `## Readiness Gate`, then write `status: approved`. If a gap cannot be settled without the user, downgrade to `council` mode instead of guessing.\n3. Record via `epic mem add --title \"Orbit: {mode} mode decision\" --type decision --importance 0.9 --body \"CONTEXT\"`\n4. **Proceed immediately to Step 3** — no approval gate\n\n## Step 2B: Council Auto-Spec (complex\u002Fvague request → council)\n\n**Use when**: PRD exists or request needs framing.\n\n1. Gather the user's request from conversation context\n2. Launch 4 parallel sub-agents (Architect, Skeptic, Pragmatist, Critic) — each receives ONLY the request + codebase context, NOT the full conversation (anti-anchoring)\n3. Synthesize: list agreement\u002Fdisagreement, produce recommended approach\n4. Generate spec at `$HARNESS_DIR\u002Fspecs\u002FSPEC-{timestamp}.md`, run the **Readiness gate** (spec skill step 3), settle every `GAP:` from the council output and record each under `## Readiness Gate`, then write `status: approved`\n5. Record via `epic mem add --title \"Orbit: council decision\" --type decision --importance 0.9 --body \"CONTEXT\"`\n6. **Proceed immediately to Step 3** — no approval gate, no \"orbit go\"\n\n## Step 2C: Interactive Mode (explicit user choice only)\n\n**Use when**: User explicitly requested interactive mode.\n\n1. Tell user to run `\u002Fdiscover` → `\u002Fspec`, then say \"orbit go\". STOP and wait.\n2. On resume: load latest `SPEC-*.md` with `status: approved`. Proceed to Step 3.\n\n**This mode is never auto-selected.** It requires explicit user opt-in.\n\n## Step 3: Build (Go)\n\n1. Load spec, extract `goal_slug`\n2. **Git preflight**: verify clean working tree and not on detached HEAD:\n   ```bash\n   [ -z \"$(git status --porcelain)\" ] || (echo \"ERROR: Dirty working tree or untracked files. Commit or stash first.\" && exit 1)\n   git symbolic-ref -q HEAD || (echo \"ERROR: Detached HEAD. Checkout a branch first.\" && exit 1)\n   ```\n3. **Worktree isolation**: Create an isolated git worktree:\n   ```bash\n   git worktree add .harness\u002Fworktrees\u002Forbit-{goal_slug} -b orbit-{goal_slug} origin\u002F{default-branch}\n   cd .harness\u002Fworktrees\u002Forbit-{goal_slug}\n   ```\n   - `.harness\u002Fworktrees\u002F` is host-neutral. Do NOT use `.claude\u002Fworktrees\u002F` —\n     it is meaningless on Codex and Antigravity.\n   - Record `worktree_name` and `original_cwd` in pipeline state\n4. Plan tasks from Requirements (R1, R2...)\n5. Execute with sub-agents — TDD, debug on failure, verify before done\n6. Handle states: DONE \u002F DONE_WITH_CONCERNS \u002F NEEDS_CONTEXT \u002F BLOCKED\n7. Integrate: full test suite, verify ACs\n\n## Step 4: Audit\n\n1. Gather scope via `git diff --stat`\n2. Classify changed files (API, Frontend, DB, Backend, Tests, Infra)\n3. Launch parallel sub-agents: Reviewer, Auditor, Test runner (+ scope-specific)\n4. Synthesize Audit Report: Quality\u002FSecurity\u002FPerformance PASS\u002FWARN\u002FFAIL + Spec Coverage\n5. **PRESERVE audit report** in pipeline state `audit_report` field\n\n## Step 5: Verdict\n\n- **All PASS + all AC verified** → proceed to Eval (if eval.yaml exists) or Ship\n- **WARN** → log, auto-proceed\n- **FAIL** → increment `audit_fail_count`:\n  - `\u003C 3`: plan fixes from action items, execute, return to Step 4\n  - `≥ 3`: **PAUSE** — ask user \"continue or abort?\"\n\n## Step 5.5: Eval (optional — only if eval.yaml or benchmarks exist)\n\n1. Check for eval config — eval is active if ANY of these exist:\n   - `$HARNESS_DIR\u002Feval\u002Feval.yaml`\n   - `benchmarks\u002Fbaselines\u002Flatest.json` in CWD (in-repo baseline)\n   - `benchmarks\u002Feval_runner.py` in CWD (auto-detected benchmark)\n2. If eval is active, run `epic eval --json` via the **eval** skill\n3. **Eval PASS** → proceed to Ship\n4. **Eval FAIL (regression detected)** → increment `audit_fail_count`:\n   - `\u003C 3`: plan fixes, execute, return to Step 4\n   - `≥ 3`: **PAUSE** — ask user \"continue or abort?\"\n5. If no eval config and no benchmarks detected, skip this step entirely\n\n## Step 6: Ship\n\n1. **Gate**: verify PASS audit report exists\n2. **Integration verification** — run directly in worktree:\n   - Clean build artifacts first: `cargo clean` \u002F `npm run clean` \u002F equivalent\n   - Full build from scratch · complete test suite · linter + formatter\n   - Fail → STOP. Do NOT create PR.\n3. **Git hygiene**: conventional commits, rebase, squash fixups\n4. **Create PR** via `gh pr create` with spec + audit report in body\n   - Record the URL in pipeline state as `pr_url`. `epic orbit unlock` warns\n     when a pipeline reaches `complete` without it.\n5. **CI watch** — probe first, then watch:\n   ```bash\n   gh pr checks \u003CPR_NUMBER> --json name,state\n   ```\n   - Checks exist → run `gh pr checks \u003CPR_NUMBER> --watch`, auto-fix failures.\n   - Empty result (no CI configured on the repo) → **skip the watch**. Log\n     \"No CI configured, skipping CI watch\", append a `phase_history` entry\n     recording `\"ci_watch\": \"skipped\"`, and proceed to Step 7 (evolve runs\n     regardless of CI outcome, so the pipeline must never wait on checks\n     that will never appear).\n6. **Exit worktree**: Return to original directory and keep the worktree\n\n## Step 7: Evolve\n\nRun the evolution engine to analyze this session and generate\u002Fimprove skills.\n\n1. **Always run** — regardless of CI outcome:\n   ```bash\n   epic-harness reflect\n   ```\n   This triggers the Ring 3 loop: observe → analyze → seed evolved skills → update metrics.\n\n   If `$HARNESS_DIR\u002Fprojects\u002F{slug}\u002Fpending_synth.jsonl` has records with `status: \"pending\"`,\n   synthesize each — launch one subagent per manifest (use your host's subagent\n   mechanism; do NOT name a model or CLI), then apply the body it produced:\n   ```bash\n   epic-harness evolve accept-synth --skill \u003Cname> --file \u003Cbody.md>\n   ```\n   Unconsumed manifests leave the template skill body in place.\n\n2. **If CI green** (all checks passed): additionally run\n   ```bash\n   epic-harness reflect --context --days 1\n   ```\n   and record the successful orbit pattern into memory:\n   ```bash\n   epic mem add --title \"Orbit: {goal_slug} succeeded\" \\\n     --type pattern --importance 0.7 \\\n     --body \"Orbit completed. Mode: {mode}. AC: all verified. PR: {url}. Stack: {stack}.\"\n   ```\n\n3. Report the evolution outcome in the final summary (evolved skills generated, score trend).\n\n4. Update pipeline state: `\"phase\": \"evolve\"`, `\"status\": \"complete\"`, then run `epic orbit unlock`.\n\n## Step 8: Report\n\n```\n## Orbit Complete\n- Pipeline: PIPELINE-{id}\n- Mode: {direct|council|interactive} (auto-detected)\n- Spec: SPEC-{timestamp} ({goal_slug})\n- Branch: orbit-{goal_slug}\n- Worktree: orbit-{goal_slug} (preserved for PR)\n- PR: {URL}\n- Audit retries: {count}\n\n### Phase Summary\n| Phase | Status | Retries |\n|-------|--------|---------|\n| Spec | approved | 0 |\n| Go | complete | 0 |\n| Audit | PASS | {count} |\n| Eval | {PASS|SKIPPED} | 0 |\n| Ship | complete | 0 |\n| Evolve | complete | 0 |\n\n### Evolution\n- Skills evolved: {count}\n- Score trend: {improving|stable|declining}\n```\n\n## Red Flags\n- Interactive mode proceeding without spec approval (direct and council modes auto-approve)\n- Continuing after 3 audit failures without user consent\n- Skipping isolated integration test\n- Shipping with FAIL in security audits\n- Losing audit report between phases\n- Creating branch with dirty working tree\n- Losing worktree reference between phases\n- Skipping evolve step after ship (evolve must always run, even if CI fails)\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002Forbit",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill orbit",{"tool":59,"command":60},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill orbit",{"tool":62,"command":63},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill orbit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002Forbit\u002FSKILL.md",true,[],[68,78,86,94,102,110],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":73,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":77},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":77},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":77},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":98,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":77},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":77},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":77},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]