Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/chrono-meta/forge-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/chrono-meta/forge-harness/fh-meta)<a href="https://agentmods.dev/plugins/chrono-meta/forge-harness/fh-meta"><img src="https://agentmods.dev/badge/plugins/chrono-meta/forge-harness/fh-meta/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/chrono-meta/forge-harness/fh-meta"><img src="https://agentmods.dev/badge/plugins/chrono-meta/forge-harness/fh-meta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
fh-meta scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "fh-meta",
"version": "3.28.0",
"engines": {
"claudeCode": ">=1.0.0"
},
"description": "New in 2.0.1: harness-doctor cadence promoted from prose to a SessionStart hook (30-day overdue check no longer silent); portability lint (BSD/GNU, zsh/bash pattern denylist) wired into pre-commit as the shell-layer sibling of the existing lints; branch_claim.sh gains an explicit warning that live-claim count is not a same-tree concurrent-edit count; the public-surface confidentiality scan's fail-open notice (operator pattern override absent) is now a hard-to-miss banner instead of a two-line aside; fh-gate.sh survives a missing package.json instead of dying under set -euo pipefail; identity ① (harness cluster) reclassified 🟢 under a redefined ⓐⓑⓒ bar (reuse is real and callable, FH did not grow to get it, sharpness is preserved via strictest-wins merge) — cross-harness adapters + relay_channel.sh --cap-args node-specific argument channel; §1-a-2's 6-axis verification canon synchronized across the file (a prior draft still said 4 in one place). New in 1.4.74: shipped documents no longer point at files the package omits. 35 such paths were measured on 2026-07-28 — CLAUDE.md instructed consumers to run templates/predelete_check.sh before a destructive op and the file did not ship. 20 more paths added; the 4 that remain absent are enumerated with a written reason each (per-environment registries and operator-private sync). Closing the set once is worth little because it regrows, so scripts/package_coverage_check.sh now fails selfcheck on any new occurrence, known-pair calibrated, and it caught itself on first wiring. New in 1.4.73: the mechanical floor now ships — templates/.git-hooks (pre-commit/pre-push) plus every script they actually invoke, their regression anchors, and the .claude/rules data they read. Until now the package shipped the prose that tells you to run the gates while omitting the gates, and 35 shipped-doc references pointed at files the tarWhat it installs
The manifest is a name and a version. 38 skills, 7 agents travel with it, and installing the plugin installs all of them — 4,109 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill steel-quench A 169 tokens
- Skill goal-quench A 180 tokens
- Skill install-wizard A 75 tokens
- Skill phantom-quench A 171 tokens
- Skill sim-conductor A 65 tokens
- Skill context-doctor A 109 tokens
- Skill harness-pr-reviewer A 61 tokens
- Skill plugin-recommender A 90 tokens
- Skill verify-bidirectional A 62 tokens
- Skill audit-learnings A 61 tokens
- Skill field-harvest A 95 tokens
- Skill frontier-digest A 92 tokens
- Skill harvest-loop A 127 tokens
- Skill pipeline-conductor A 108 tokens
- Skill public-surface-audit A 97 tokens
- Skill salience-splitter A 96 tokens
- Skill asset-placement-gate A 55 tokens
- Skill dialogue-harvest A 165 tokens
- Skill edit-manifest A 76 tokens
- Skill return-path-gate A 91 tokens
- Skill contention-layer A 129 tokens
- Skill marketplace-gate A 44 tokens
- Skill memory-hygiene A 65 tokens
- Skill meta-prompt-builder A 77 tokens
- Skill prompt-regression A 106 tokens
- Skill apex-review A 53 tokens
- Skill video-ingest A 140 tokens
- Skill deep-clarify A 77 tokens
- Skill fh A 47 tokens
- Skill pr-review-watcher A 53 tokens
- Skill frontier-status-summary A 39 tokens
- Skill persona-roster-expander A 52 tokens
- Skill corpus-grounding-expander A 40 tokens
- Skill harness-doctor B 83 tokens
- Skill cross-ecosystem-synergy-detection B 79 tokens
- Skill install-doctor B 83 tokens
- Skill auto-decorrelation C 148 tokens
- Skill agent-composer C 74 tokens
- Agent persona-innovator A 61 tokens
- Agent challenger A 102 tokens
- Agent expert A 114 tokens
- Agent main-player A 123 tokens
- Agent beginner A 117 tokens
- Agent fact-checker A 69 tokens
- Agent hub-persona-auditor A 89 tokens
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed c051954e64f3
- 4d ago Changed af7d3669014e
- 6d ago Changed 515d34111f2c
- 7d ago Changed 824cd6acd4f5
- 8d ago Changed 977d3849c732
- 11d ago Changed 6790365786f5
- 20d ago Changed f9eab0ef3d36
- 21d ago Changed bf17e46e9e2d
- 22d ago Changed 297047476735
- 23d ago First seen · 37 lines scan A aa0b8a08c5f2
fh-meta is a plugin published in the GitHub repository chrono-meta/forge-harness (30 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
harness-zh
A Chinese-language design guide for creating teams of specialised coding agents and the skills they use. It is intended for Claude Code and focuses on simplified Chinese.
hipocampus
Persistent agent memory that survives across sessions — auto-compacting 3-tier memory with hybrid search. Your agent remembers what it learned, decided, and built.
relay
Delegate work packets from a lead Claude Code session to executor sessions in their own iTerm tabs, with session reuse instead of always spawning fresh.
research-papers
Annotated research paper collection management — retrieve, read, extract, cross-reference scientific papers.
the-council
Catch blind spots in architecture decisions with multi-perspective analysis that learns from your project history.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.