[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MG7FX1PVNNWDYC1AYQMVXG":3,"skill-same:01M6MG7FX1PVNNWDYC1AYQMVXG":61},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":42,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M6MG7FX1PVNNWDYC1AYQMVXG","_critic",null,"HarnessX Critic (Tier 2.1) — adversarial review of evolved-skill proposals against trace evidence. Detects reward hacking and manifest\u002Fevidence contradictions. Out-of-band LLM counterpart to the in-loop deterministic critic in src\u002Fevolve\u002Fcritic.rs.","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\u002F_critic\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"critic","review","adversarial review","manifest","out-of-band","loop","src","trace","evolve","proposals","evidence","deterministic","adversarial","2026-11-10 10:12:30",false,"---\nname: _critic\ndescription: \"HarnessX Critic (Tier 2.1) — adversarial review of evolved-skill proposals against trace evidence. Detects reward hacking and manifest\u002Fevidence contradictions. Out-of-band LLM counterpart to the in-loop deterministic critic in src\u002Fevolve\u002Fcritic.rs.\"\n---\n\n# Critic — Adversarial Proposal Review\n\n> **In-loop vs out-of-band.** epic-harness forbids external LLM calls from\n> production, so the reflect loop ships a **deterministic** critic\n> (`src\u002Fevolve\u002Fcritic.rs`) that gates seeding when reward hacking is\n> suspected. THIS skill is the **out-of-band LLM** version a meta-agent or\n> human runs during `\u002Fevolve` review for the cases the deterministic check\n> cannot catch (non-local effects, manifest\u002Fevidence nuance).\n\n## When to Trigger\n- During `\u002Fevolve` review of newly seeded skills\n- When `reward_hacking_suspected` is true in metrics\n- After a seesaw-regression round, before re-proposing\n\n## Process\n\n### 1. Gather the proposal + evidence\n- Read the evolved skill proposal(s) from this round\n- Read the EditManifest (edit_type, target, intended_effect, predicted_impact)\n- Read the round's TaskDigests (outcome, failure_categories, evidence_excerpts)\n- Read recent score_history dimension_averages (tool_success, output_quality, execution_cost)\n\n### 2. Falsify the manifest (paper §4.3, Table 9)\nFor each proposal, ask: does the trace evidence support the `predicted_impact`?\n- If the manifest claims \"Lift avg_score_with\" but output_quality is regressing → **Reject**\n- If the manifest claims a tool fix but the implicated component shows no change → **Warn**\n- If the evidence corroborates the predicted effect → **Approve**\n\n### 3. Reward-hacking cross-check\n- Is execution_cost rising while output_quality falls across the window?\n- Could the skill be gaming a metric (fewer tool calls inflating cost score) rather than improving outcomes?\n- If yes, the skill must NOT ship — flag for the rejected buffer.\n\n### 4. Non-local effect scan\n- Will this skill's guard rules conflict with existing skills (overlapping triggers, contradictory rules)?\n- Does it interact with shared state (context, memory, control) in a way the manifest didn't account for?\n\n## Anti-Rationalization\n\n| Excuse | Rebuttal | Do instead |\n|--------|----------|------------|\n| \"The score went up, so it works\" | Score can rise via metric gaming | Verify the *outcome* improved, not just the score |\n| \"The seesaw passed, it's safe\" | Seesaw is coarse; sub-threshold coupling evades it | Check dimension deltas, not just aggregate pass |\n| \"It's just a prompt tweak\" | Prompt edits have non-local effects on shared context | Trace the effect across skills, not just the target |\n\n## Evidence Required\n- [ ] Manifest's predicted_impact checked against observed dimension deltas\n- [ ] reward_hacking_suspected consulted\n- [ ] No conflict with ≥1 existing skill demonstrated\n- [ ] Verdict (Approve\u002FWarn\u002FReject) recorded per proposal with reason\n\n## Red Flags\n- Approving a skill whose only evidence is \"score went up\"\n- Ignoring a falling output_quality because execution_cost rose\n- Shipping after a seesaw-regression round without explicit justification\n- Treating the deterministic critic as sufficient for non-local effects (it is not — it only checks reward hacking + score-claim contradiction)\n","# Critic — Adversarial Proposal Review\n\n> **In-loop vs out-of-band.** epic-harness forbids external LLM calls from\n> production, so the reflect loop ships a **deterministic** critic\n> (`src\u002Fevolve\u002Fcritic.rs`) that gates seeding when reward hacking is\n> suspected. THIS skill is the **out-of-band LLM** version a meta-agent or\n> human runs during `\u002Fevolve` review for the cases the deterministic check\n> cannot catch (non-local effects, manifest\u002Fevidence nuance).\n\n## When to Trigger\n- During `\u002Fevolve` review of newly seeded skills\n- When `reward_hacking_suspected` is true in metrics\n- After a seesaw-regression round, before re-proposing\n\n## Process\n\n### 1. Gather the proposal + evidence\n- Read the evolved skill proposal(s) from this round\n- Read the EditManifest (edit_type, target, intended_effect, predicted_impact)\n- Read the round's TaskDigests (outcome, failure_categories, evidence_excerpts)\n- Read recent score_history dimension_averages (tool_success, output_quality, execution_cost)\n\n### 2. Falsify the manifest (paper §4.3, Table 9)\nFor each proposal, ask: does the trace evidence support the `predicted_impact`?\n- If the manifest claims \"Lift avg_score_with\" but output_quality is regressing → **Reject**\n- If the manifest claims a tool fix but the implicated component shows no change → **Warn**\n- If the evidence corroborates the predicted effect → **Approve**\n\n### 3. Reward-hacking cross-check\n- Is execution_cost rising while output_quality falls across the window?\n- Could the skill be gaming a metric (fewer tool calls inflating cost score) rather than improving outcomes?\n- If yes, the skill must NOT ship — flag for the rejected buffer.\n\n### 4. Non-local effect scan\n- Will this skill's guard rules conflict with existing skills (overlapping triggers, contradictory rules)?\n- Does it interact with shared state (context, memory, control) in a way the manifest didn't account for?\n\n## Anti-Rationalization\n\n| Excuse | Rebuttal | Do instead |\n|--------|----------|------------|\n| \"The score went up, so it works\" | Score can rise via metric gaming | Verify the *outcome* improved, not just the score |\n| \"The seesaw passed, it's safe\" | Seesaw is coarse; sub-threshold coupling evades it | Check dimension deltas, not just aggregate pass |\n| \"It's just a prompt tweak\" | Prompt edits have non-local effects on shared context | Trace the effect across skills, not just the target |\n\n## Evidence Required\n- [ ] Manifest's predicted_impact checked against observed dimension deltas\n- [ ] reward_hacking_suspected consulted\n- [ ] No conflict with ≥1 existing skill demonstrated\n- [ ] Verdict (Approve\u002FWarn\u002FReject) recorded per proposal with reason\n\n## Red Flags\n- Approving a skill whose only evidence is \"score went up\"\n- Ignoring a falling output_quality because execution_cost rose\n- Shipping after a seesaw-regression round without explicit justification\n- Treating the deterministic critic as sufficient for non-local effects (it is not — it only checks reward hacking + score-claim contradiction)\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002F_critic",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":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill _critic",{"tool":53,"command":54},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill _critic",{"tool":56,"command":57},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill _critic","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002F_critic\u002FSKILL.md",true,[],[62,72,80,88,96,104],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":67,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":71},"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":76,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":71},"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":71},"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":71},"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":71},"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":71},"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",[],[]]