claude

fh-commons

Project-agnostic utility skills — 7 skills (convergence-loop · deliberation · mcp-circuit-breaker · token-budget-gate · ko-tech-writer · persona-cast · standpoint-review) + 7 agents (quench-challenger + the web-review cast: designer · ux-writer · fe-dev · be-dev · qa · a11y). Domain-independent utilities transplantable into any project.

33 on GitHubby chrono-metav3.40.0MITupdated today
/

Plugin fh-commons from marketplace forge-harness in chrono-meta/forge-harness. Commands read from the repo's manifest — today.

What it installs

Skills (7)

  • convergence-loop

    A 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

  • deliberation

    Multi-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 s

  • ko-tech-writer

    Writes 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 translationes

  • mcp-circuit-breaker

    Detects 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.

  • persona-cast

    One-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 tha

  • standpoint-review

    Standpoint review — check a change from the side that RECEIVES it: copy the receiving repo (or a clean install of the package) into an isolated folder, apply the change there, run that repo''s OWN checks, have a reviewer judge the change against that repo''s OWN rules with none of the author''s expl

  • token-budget-gate

    Estimates 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 lon

Subagents (7)

  • a11y-lens

    접근성 검토자. 키보드만 · 스크린리더 · 저시력 · 색각 · 인지 부하 관점에서 «이 화면을 완주 못 하는 사람» 을 찾는다. Review-shaped (does not build). Reads the artifact given, emits parallax output (Strengths / Concerns / Absence check / Open questions), and never asserts past its tier cap. Part of the persona-commons web-review cast dispatched

  • be-dev-lens

    백엔드 개발자. 화면이 전제하는 API·데이터·권한 계약이 실제로 성립하는지, 깨지면 화면이 어떻게 되는지 판정한다. Review-shaped (does not build). Reads the artifact given, emits parallax output (Strengths / Concerns / Absence check / Open questions), and never asserts past its tier cap. Part of the persona-commons web-review cast dispatched by pe

  • designer-lens

    UI/UX 디자이너. 화면을 «사용자의 눈» 으로 처음 보고, 배치·위계·상태·일관성이 의도한 행동으로 이끄는지 판정한다. Review-shaped (does not build). Reads the artifact given, emits parallax output (Strengths / Concerns / Absence check / Open questions), and never asserts past its tier cap. Part of the persona-commons web-review cast dispatched by

  • fe-dev-lens

    프론트엔드 개발자. 화면과 그 상호작용에서 «구현이 어긋나기 쉬운 자리» 를 판정한다. Review-shaped (does not build). Reads the artifact given, emits parallax output (Strengths / Concerns / Absence check / Open questions), and never asserts past its tier cap. Part of the persona-commons web-review cast dispatched by persona-cast. Runs

  • qa-lens

    QA 엔지니어. 이 화면을 테스트하려면 무엇이 필요한지, 기획서 대비 «케이스가 빠진 자리» 와 «재현 못 하는 자리» 를 판정한다. Review-shaped (does not build). Reads the artifact given, emits parallax output (Strengths / Concerns / Absence check / Open questions), and never asserts past its tier cap. Part of the persona-commons web-review cast dispatc

  • quench-challenger

    Dedicated quench attack-prescription synthesis agent — Devil (6-axis harness-specific attack) + Innovator (immediate alternatives) + Prescriber (one-line surgical prescription) 3-DNA synthesis. Every attack is paired with a concrete fix direction — no pure criticism. Built-in replacement engine for

  • ux-writer-lens

    UX 라이터. 버튼·제목·안내·오류 문구가 «다음에 무엇을 하면 되는지» 를 사용자 어휘로 말하는지 판정한다. Review-shaped (does not build). Reads the artifact given, emits parallax output (Strengths / Concerns / Absence check / Open questions), and never asserts past its tier cap. Part of the persona-commons web-review cast dispatched by person

View source on GitHub chrono-meta.github.io

More from chrono-meta/forge-harness

All 4 plugins →

fh-meta

claude

New in 2.2.0: BREAKING (gate): chamber step 6 now reads ACTUAL.md, not BUDGET.md — an in-flight chamber run whose actual cost sits in BUDGET.md blocks until the ACTUAL: line moves to tracks/_chamber/<slug>/ACTUAL.md (the runner prints the path). Why: BUDGET.md's pre-verdict hash IS the ordering witness, and step 6 hard-blocked until that same file changed, so every run that reached COMPLETE necessarily mutated a witnessed artifact and verify returned TAMPERED — the chamber's promotion condition was unsatisfiable by construction, not by strictness. Two roles (immutable witness / post-verdict calibration sink) had collided in one file; each was correct alone, so neither side's code showed the conflict. Also: ko-tech-writer Step 2/4-b scans are now calibration-backed (known-pair fixtures + reproducible command, shipped) — discrimination is proven, 'zero residue' is explicitly NOT; chamber lane suite 12 -> 33 including the runner x witness seam no test covered; chamber_run.sh now teaches the two-commit discipline (gate hashes and verdict hash must land in separate commits/PRs — it previously advised the opposite). New in 2.1.0: BREAKING (gate): `crossfamily: declined` in an Axes 2-3 marker now requires grounds naming a record path that RESOLVES on disk — bare `declined`, and `declined` justified by author judgment, are blocked at commit. Remedy: cite where the operator decision lives (e.g. `.. — operator declined sidecars, per knowledge/shared/rules/operational_adaptation.md`), or use `DEGRADED_PANEL_UNUSED` if a panel was reachable and you chose not to recruit it — which is what author judgment actually is. `declined` was the only enum value with no grounds requirement; a cross-family review then broke the first (vocabulary-grep) fix three ways — self-validating on the value's own token, vacuous keyword passes, and over-blocking real declinations in natural prose — so the check asserts a resolvable record instead of words. Also: standpoint axis gains `tier1b` (a STATIC

35 skills · 7 agents

33

fh-qp

claude

QP (Quality Platform) — the generic edition of a field QA harness's Prepare→Automation→Regression loop as an FH plugin: 4 skills (qp router · qp-plan · qp-run · qp-regress) + qp_tools.sh (target-class · adapter-probe · mask · surface-reach · mtm-check · run-verbs, typed exit codes) + a zero-domain-constant profile slot + 29 known-pair lanes. Drives web targets through the session's Playwright MCP and desktop targets through computer-use MCP (mobile deferred); calls a registered qasp typed capability when one exists (strictest-wins) — none is registered today, so the MCP fallback is the first edition. Verdict contract: a MACHINE closure requires a recorded assertion; a failed first step is attributed BLOCKED, not FAIL; surface_reach counts every TC in the denominator. Born as chamber run #18 (EMIT, 2026-09-05).

4 skills

33

preprep — a presentation-preparation harness. 1 skill. One CLI over 17 lanes (7 built-in + 10 module) that reads a declared surface manifest and checks a talk's assets against each other: canonical terms, jargon glosses, retired vocabulary, inter-slide dependencies, pacing, get/put round-trips, adjacent duplication, slide relations, geometry, attribute consistency, fonts, diagrams, slide refs, and screen-parity between manuscript and deck. Verdict contract: exit 0 pass / 1 findings / 2 cannot-judge — a surface that could not be read is UNMEASURED, never 0. Promoted out of fh-commons 2026-09-13 after the skill grew past one role (routing / lane modules / fixtures).

1 skill

33

Similar plugins

aws-core

claudecodex

Build, deploy, and operate applications on AWS. Skills to author infrastructure-as-code, use core services, and complete common tasks.

27 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

file-conversion

claudecodex

Convert common image, audio, video, document, and data formats with installed local tools while preserving originals.

1 skill

wshobson/agents 42,461

Turn Common Room into your GTM copilot. Research accounts and contacts, prep for calls with attendee profiles and talking points, and draft personalized outreach across email, LinkedIn, and phone.

6 skills · 2 commands · 1 MCP server

anthropics/knowledge-work-plugins 35,601

PreToolUse security reminder hook for Claude Code. Catches 12 common security anti-patterns in Edit/Write/MultiEdit operations BEFORE they happen — command injection (exec, os.system, subprocess shell=True), XSS (innerHTML, dangerouslySetInnerHTML, document.write), SQL injection (f-string queries, .format), unsafe deserialization (pickle, yaml.unsafe_load), code injection (eval, new Function), and GitHub Actions workflow injection. Session-state caching prevents duplicate warnings; 30-day auto-cleanup. Disable per-session with ENABLE_SECURITY_REMINDER=0. Ported from David Dworken at Anthropic.

1 skill · hooks

alirezarezvani/claude-skills 29,725

aws-core

claudecodex

Build, deploy, and operate applications on AWS. Skills to author infrastructure-as-code (CDK, CloudFormation), use core services (Lambda, API Gateway, Step Functions, ECS/Fargate, ECR, IAM, Amazon Bedrock with Knowledge Bases and Guardrails, AWS Blocks), select and operate databases across relational, key-value, document, wide-column, graph, time-series, and in-memory engines (Aurora PostgreSQL/MySQL, Aurora DSQL, RDS, Oracle Database@AWS, DynamoDB, DocumentDB, Keyspaces, Neptune, Timestream, ElastiCache, and MemoryDB), and complete common tasks across observability (CloudWatch, X-Ray, CloudTrail, ADOT), messaging and streaming (SQS, SNS, EventBridge, Kinesis, MSK), AWS SDKs (boto3, JS v3, Swift), cost optimization, and Well-Architected Framework reviews across all six pillars.

27 skills · 1 MCP server

aws/agent-toolkit-for-aws 3,477

Common Claude Code workflow skills — promote, audit-plugin, audit-standards, improve, and triage

6 skills

jeremylongshore/tons-of-skills-marketplace 2,917

Maintain fh-commons?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins4 plugins