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.
npx agentmods add skills/chrono-meta/forge-harness/fhnpx skills add chrono-meta/forge-harness --skill fhgit 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/skills/chrono-meta/forge-harness/fh)<a href="https://agentmods.dev/skills/chrono-meta/forge-harness/fh"><img src="https://agentmods.dev/badge/skills/chrono-meta/forge-harness/fh.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.01530 |
| Opus 5 | $0.00023 | $0.00765 |
| Sonnet 5 | $0.00009 | $0.00306 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
fh 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 6d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fh — hub map on demand
The greeting flow (CLAUDE.md §Active Onboarding) fires on greetings, start intents, new-task and discovery utterances — but it is salience-dependent, once-per-session, and skipped entirely when the user opens with a task. This command is the explicit, deterministic route to the same map: slash autocomplete discoverability, invocable mid-session any number of times, no reliance on the model catching a phrase. Same map, different guarantee — /fh does not claim a gap in which utterances fire onboarding; it closes the how-reliably-and-when gap.
Execution Steps
Step 1. State detection (reuse, don't re-derive)
Run the same mechanical branch test as §Active Onboarding: session files / mapped project tracks
under tracks/ (underscore dirs don't count) → new / returning; FH-dev state (session card ·
open fh_signal_* · CLAUDE.local.md) → operator. Do not invent a separate test — the canonical
branch rules live in CLAUDE.md §Active Onboarding and fh_detail_protocols.md Step 2.
Step 2. Render the door menu
Output the door skeleton for the detected branch verbatim from the canonical source (CLAUDE.md §Active Onboarding — including the 🐿️ same-line welcome). Compose door ③ / 🔧 candidates live from the session card and CATALOG, exactly as the greeting path would.
Step 3. Render the quick map (below the menu)
- Starter set: the curated first-five from
templates/starter_profile.md(read it — do not hardcode a list that can go stale), one line each. - Most-used phrases: 5-8 rows from CHEATSHEET §4 (universal phrases + the full-autonomy contract line).
- If cwd is a mapped field project: one line noting "진단해줘" routes to the Field-Harness Diagnostic here.
Step 4. Hand off
End with "pick a door, say a phrase, or just state your task". Do not auto-run anything — this command is a map, not a dispatcher.
Step 3.5 — 가이드 · Q&A (📖 문을 골랐을 때만 진입)
🟥 Q&A 는 net-new 기능이 아니다. FH 에 대해 묻고 답하는 것은 이미 된다(CLAUDE.md 가 상주라 세션이 문·게이트·스킬을 안다). 이 절이 더하는 것은 하나뿐이다 — 「무엇을 근거로 답하나, 그리고 없으면 없다고 말한다」는 계약. 그래서 새 스킬을 만들지 않고 여기 붙인다.
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.
- 6d ago First seen · 107 lines · 47 tokens per session scan A 88bd9ba92d38
fh is a skill published in the GitHub repository chrono-meta/forge-harness (14 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,530 once invoked, about $0.0002 per session on Opus 5. 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 skills, from other repositories
reconcile
Cross-reference a paper against the collection. Finds which cited papers are already collected, which are new leads, which collection papers cite this one, and reconciles all cross-references bidirectionally. Run on a single paper directory or use --all for the entire collection.
adjudicate
Systematically adjudicate disagreements across a paper collection. Produces ruthless verdicts on who was wrong, what supersedes what, and what the best current understanding is. Organized by topic clusters with actionable replacement values for implementation.
author-context
Create a propstore context for one paper with CEL assumptions, parameters, and perspective. Every claim extracted from the paper will reference this context. Required before extract-claims if the paper does not already have one.
author-rules
Author the DeLP rule artifacts (strict, defeasible, properdefeater, blockingdefeater) encoding a paper's stated argument structure. Runs after register-predicates.
extract-claims
Extract propositional claims from a paper directory into the propstore source branch using pks source propose-claim.
paper-retriever
Retrieve a scientific paper PDF given an arxiv URL, DOI, or paper title. Downloads to papers/ directory. Handles open-access retrieval (arxiv direct, Chrome print-to-pdf for publisher-direct HTML, Unpaywall, title-based open-repository search); for paywalled papers it hands off to whichever paper-retriever- access…