FH is a meta-harness for Claude Code: it helps you build harnesses and skills — the rules, gates and memory a project needs — and checks them before they ship.
安装
npx skills add chrono-meta/forge-harnessgh skill install chrono-meta/forge-harnessgit clone --depth 1 https://github.com/chrono-meta/forge-harness合集内的技能
- Agent Composerchrono-metaReads the current work context and plans the optimal agent dispatch. Clarifies direction with 1-2 questions when unclear; infers and proceeds immediately when execution path is unclear. Runs an automatic recording gate after each Wave completes. Triggered by "compose agents", "which agent should I use?", "run in parallel", or "agent-composer".
- Apex Reviewchrono-metaReviews a technical proposal from the perspective of organizational decision-makers (CTO, technical lead, QA lead, conference reviewers, etc.) and generates an HTML presentation deck. Outputs approval gate results per persona and connects to sim-conductor for improvement suggestions.
- Asset Placement Gatechrono-metaRoutes a proposed skill, plugin, or agent to its correct home — forge-harness (FH) meta-skill, project-local agent, or drop — by applying a 4-criteria meta-skill bar followed by a project-local value test.
- Auto Decorrelationchrono-metaRecruits cross-family verifier sidecars (codex, agy, local 4090 over Tailscale) for adversarial verification of load-bearing changes, maximizing model-family diversity against the orchestrator. Mechanically discovers the available sidecar panel, recruits at least one cross-family verifier when present, and degrades gracefully when none are.
- Contention Layerchrono-metaWhen two skills, agents, or independent research tracks produce conflicting verdicts on the same output, reads the conflict as a signal rather than an error and harvests new skill candidates or insight deltas — including a Dual-Track Grounding conflict (open-frontier track vs internally-grounded recall track disagreeing).
- Context Doctorchrono-metaReduces token waste in Claude Code sessions (run the built-in `/context` first; this skill covers what it does not) across two axes — context footprint (auto-generates .claudeignore, guides over-read files and /clear timing) and command output (routes to a command-output proxy/hook such as rtk to trim verbose CLI stdout).
- Convergence Loopchrono-metaA universal gate-reinforcement meta-skill that replaces the "single-pass = done" pattern with a converging loop of up to N rounds. Can be applied to any gate, checkpoint, or verification step. Only declares "truly passed" after FAIL→FIX→re-verify repeats until convergence (all items pass). Escalates to structural redesign if not converged within N rounds.
- Corpus Grounding Expanderchrono-metaFetches and normalizes multi-version public-domain corpora into a single verified-axiom store for verbatim-relay grounding, recording per-version license and provenance.
- Cross Ecosystem Synergy Detectionchrono-metaAutomatically discovers useful combinations (synergy pairs) across multiple installed plugins and skills, and presents them as a ranked table. Proactively suggests undiscovered synergies when new projects or skills are registered in the registry. Activates on phrases like "do my installed tools work well together?", "they seem to work in isolation", "find synergies".
- Deep Clarifychrono-metaClarifies ambiguous requests through Socratic dialogue, drawing out goals, completion criteria, and constraints to produce a structured spec document. Pre-dispatch requirement clarification step for agent dispatch. Triggered by "I don't know what to build", "how should I approach this", "organize this for me", "clarify this", "deep-clarify".
- Deliberationchrono-metaMulti-perspective synthesis structure — Innovator (propose) → Devil-Advocate (challenge) → Mediator (synthesize) 3-layer execution. Outputs conditional verdicts without binary win/loss. Activates on "deliberation", "battle this out", "weigh the pros and cons", "review from multiple angles", "which side is right?". Optional deep-insight persona jurors for domain-specific views.
- Dialogue Harvestchrono-metaMines improvement insights from long-form AI dialogue logs and long texts — an external or pasted corpus, not the current session (current-session wrap-up belongs to harvest-loop). First operation is sycophancy removal — separates speakers, strips the counterpart's agreement/restatement spans, converts the user's own utterances into falsifiable propositions, and labels each proposition induced…
- Edit Manifestchrono-metaImplements a predict-verify loop for harness edits. Every SKILL.md, rules/*.md, or CLAUDE.md change is paired with a predicted impact stored in a manifest. The next session verifies predictions against actual outcomes, and a validation gate accepts edits only when improvement is measurable. Runs automatically on harvest-loop Step 0-c and on explicit invocation.
- Fhchrono-metaRenders the FH hub map on demand — the door menu, a starter set of skills, and the most-used trigger phrases — without requiring a greeting. State-aware; composes live candidates from the session card and tracks.
- Field Harvestchrono-metaScans git history of field projects to detect patterns worth backporting to the meta-harness (Mode A), and logs session work to the knowledge hub when a session ends (Mode B). Triggers on "save this pattern", "make this reusable across projects", "can we automate this repetition?", "push this to FH", "reverse absorption", "harvest pattern", "session log", "log today's work", "sync to hub".
- Frontier Digestchrono-metaCollects the latest AI/harness engineering trends from HackerNews, arxiv, launch channels (Launch YC, Product Hunt, Show HN), GeekNews and vendor changelogs, then synthesizes them into actionable insights directly relevant to forge-harness operations. Triggered by "AI trends", "latest trends", "this week's AI updates", "what's on the frontier", "harness trends", "frontier-digest".
- Goal Quenchchrono-metaWraps /goal with a tiered safety + orchestration ladder. core (default): a token budget gate (pre-run estimate), mid-run budget thresholds, and an automatic post-run quality verification via pipeline-conductor — closing /goal's two gaps (the runner's per-turn judge evaluates completion, pipeline-conductor evaluates correctness).
- Harness Doctorchrono-metaScans a project's harness structure (.claude/ directory, CLAUDE.md, rules, agents) to diagnose complexity, drift, missing files, and broken references, then suggests improvements. `--lint` flag adds language-pattern scan (self-marketing, cushion words, version brags). Triggered by "harness check", "structure diagnosis", "CLAUDE.md audit".
- Harness Pr Reviewerchrono-metaChecks a submitted PR against the environment's baseline assets (CLAUDE.md, memory, naming, asset classification) and attaches a review comment with a merge recommendation. 5 steps — diff read, 8-area consistency check, self-catch, comment, merge recommendation.
- Harvest Loopchrono-metaAn 8-step self-evolution pipeline that runs after field sessions end (field-harvest → contention-layer → challenger + persona-innovator → synthesizer → Critic agent → harness-doctor → verify-bidirectional → curator), absorbing session learnings back into the FH ecosystem. Runs automatically at session end in the main dev environment; proposes execution first for external users.
- Install Doctorchrono-metaScans the existing environment (after the built-in `/doctor` — this covers FH-plugin conflicts it does not) before and after meta-harness plugin install to diagnose conflicts, duplicates, and silent overwrite risks. Reports potential conflict areas with existing CLAUDE.md, skills, hooks, and audit practices. Activates on "install conflict", "any overlaps?", "is it safe to install?".
- Install Wizardchrono-metaRun when setting up a new project for the first time or onboarding after installing FH (first setup, initial configuration, onboarding start, configure project, help me set up). Performs environment detection → gap diagnosis → item-by-item suggestions → user approval → execution → acceleration baseline setup in sequence. Use --dry-run to output diagnosis report only (bg dispatch compatible).
- Ko Tech Writerchrono-metaWrites or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a…
- Marketplace Gatechrono-metaEvaluates whether a repository meets marketplace listing criteria via a 5-point check and outputs a listing suitability verdict. Checks README completeness, zero-config readiness, maintenance signals, duplication, and public safety.
- MCP Circuit Breakerchrono-metaDetects MCP tool failure patterns and trips a circuit breaker to stop cascading retries. Proposes fallback alternatives and resets when the tool recovers. Triggers on "MCP failing", "tool keeps erroring", "circuit-breaker", repeated tool call failures.
- Memory Hygienechrono-metaDetects "stale-but-confident" memory entries — facts that were once verified but have silently drifted. Scans memory/*.md for entries past their staleness threshold and proposes re-verification or archival. Runs automatically as part of harvest-loop Step 0-c and on explicit invocation.
- Meta Prompt Builderchrono-metaGenerates structured prompts to send to each agent in an agent dispatch plan. Triggered by "write the instructions", "what do I say to the agent?", "write the prompt for me", "meta-prompt-builder". Bridges agent-composer (which agents) and prompt content (what to say). Uses Goal/Context/Constraints/Done When structure.
- Persona Castchrono-metaOne-line doorway that lets a field harness review an artifact (a screen, a spec, a PR, a page) through a pre-built cast of review-shaped personas — web-review cast by default (designer, ux-writer, fe-dev, be-dev, qa, a11y) — dispatched in isolation, merged with a marginal-coverage stop so a lens that finds nothing unique is reported as decorative, not padded.
- Persona Roster Expanderchrono-metaExpands a named persona seed into a tiered, judgment-mapped cast — tiering each persona by a domain safety rule, mapping each to a decision-lens in the user's vocabulary, then proposing additional voices with sourced anchors.
- Phantom Quenchchrono-metaInput-tracing grounding audit for artifacts such as test cases, analysis reports, and design docs. Extracts proper nouns, numbers, citations, version claims, and branching conditions, then back-traces each to declared local files by grep or to external sources by fetch-and-support checks. Marks missing anchors as Phantom Claims and cited-but-unsupporting anchors as Unsupported.
- Pipeline Conductorchrono-metaChains the four core FH verification pipelines (harvest-loop → steel-quench → phantom-quench → sim-conductor) into a single gated sweep. Accepts a scope (single skill, specific asset, full harness) and aggregates results into one structured report. Supports --quick mode (steps 2+3 only) and --full mode (all four steps).
- Plugin Recommenderchrono-metaGiven a task description, searches internal and external open-source ecosystems (including Codex marketplace and Claude Code marketplace) to find and recommend suitable plugins with installation guidance. Recommendation is quality-validation based (marketplace-listed + performance-validated), not source-origin based.
- Preprepchrono-meta한국식 발표대본과 장표에 특화된 준비 하네스. 레퍼런스를 먼저 묻고(공식 장표가이드 · 참고 덱), 대화로 주제·구성·전개를 세운 뒤, 기승전결 배치안을 «여러 개» 내고 사람이 고른다. 제작 후 바닥 검사 — 금지 인용이 어느 면에 남았나, 원고와 노트의 단위 참조가 갈렸나, 재생성이 사람 편집을 삼켰나, 장 사이 의존이 깨졌나, 조어가 낭독면 첫 등장에 풀이를 달았나, 장당 발화가 상한을 넘었나. 리허설 녹화를 들으면 쉼·접속사·문장 끝 억양·끝인사 크기를 코칭 표로 낸다(advisory).
- Prompt Regressionchrono-metaStatically checks harness assets against a known-answer probe set after rule/skill changes — inspects the changed source for the trigger phrases, chain links and gate conditions each probe expects, and reports PASS/FAIL/SKIP per probe. Source inspection only; it does not run live sessions, so it catches assets that no longer SAY the right thing, not models that stop DOING it.
- Public Surface Auditchrono-metaScans git-tracked (public) files for operator-private tokens that should live only in gitignored files — real usernames, absolute home paths, companion-store names, company asset names. Reports file:line + matched token + severity, so a public/private split stays clean before publish.
- Qpchrono-metaQP (Quality Platform) router — takes a web URL or a desktop app name and runs the plan → run → regress loop (qp-plan, qp-run, qp-regress) end to end, or routes to one stage. Classifies the target (public vs profile-required), probes which adapter the session has (Playwright MCP for web, computer-use MCP for desktop), and writes every artifact with a typed engine/adapter marker.
- Qp Planchrono-metaPrepare stage of QP — builds a surface inventory of a web page or desktop app (routes, menus, forms, dialogs), checks it is MECE (no overlap, nothing missing that is visible), and designs test cases as a TSV with preconditions and expected values whose SOURCE is named. Works without a spec document (then expected values come from the inventory, not a plan).
- Qp Regresschrono-metaRegression stage of QP — re-executes a previous run's test cases unchanged, computes surface_reach (how many TCs left the entry screen, as a ratio over ALL TCs), and reports the per-TC delta against the earlier run so a "no change" claim is per case, not an aggregate.
- Qp Runchrono-metaAutomation stage of QP — executes the test cases from qp-plan against the live app through the session's adapter (Playwright MCP for web, computer-use MCP for desktop), records one verdict per step with a closed status, an MTM branch, whether the step was closed by machine evidence or left to judgment, and masks emails/tokens/passwords out of the evidence before saving.
- Return Path Gatechrono-metaAudits SKILL.md files in plugins/ for return-path gate compliance. Detects fire-and-forget chains where a caller dispatches a downstream skill but does not gate its next step on the callee's verdict. Reports each chain as CLOSED or OPEN and outputs specific fix suggestions.
- Salience Splitterchrono-metaSplits an over-loaded always-loaded context asset (SKILL.md, CLAUDE.md, memory index) into a lean resident layer plus an on-demand layer, by when content is needed rather than by length, linked by imperative pointers. Alias: skill-splitter. Triggers: "SKILL.md too large", "split this skill", "skill is bloated", "skill file too long", "CLAUDE.md 너무 커".
- Sim Conductorchrono-metaAutonomously runs external user reaction simulations, internal audits, ideation scans, artifact validation, and quality reviews. Profiles the target artifact first, then derives task-appropriate personas, dispatches them as parallel agents, classifies findings into M/S/R tiers, and completes the pipeline through to commit automatically.
- Steel Quenchchrono-metaAll-angle verification meta-skill for near-complete artifacts. Turns vague design anxiety into structured challenger waves using fh-commons:quench-challenger, then drives defense and convergence until root weaknesses, residual risks, and added complexity are explicit.
- Token Budget Gatechrono-metaEstimates token cost before a multi-step task and outputs a 4-tier Green/Yellow/Orange/Red gate verdict. Records actual vs. estimated after completion when a mechanical usage source exists. Triggers on "token budget", "how much will this cost", "will this be expensive", "estimate tokens", before long multi-agent tasks.
- Verify Bidirectionalchrono-metaA skill that immediately updates the baseline and reflects it in the next session when the user raises a counter-argument to an AI recommendation. Triggered by "is that right?", "re-examine this", "something seems off here". Explicit /verify-bidirectional call also possible.
- Video Ingestchrono-metaIngests a video's content (YouTube and similar) for agent context, routing by capability, task need, and video length — a natively multimodal engine (Gemini via agy or the Gemini API) for direct-URL and long video, Claude vision over ffmpeg-extracted frames when no such engine is present, yt-dlp captions when the transcript alone suffices, and the logged-in claude-in-chrome session for…