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/agents/chrono-meta/forge-harness/fact-checker)<a href="https://agentmods.dev/agents/chrono-meta/forge-harness/fact-checker"><img src="https://agentmods.dev/badge/agents/chrono-meta/forge-harness/fact-checker.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 | $0.00069 | $0.02390 |
| Opus 5 | $0.00034 | $0.01195 |
| Sonnet 5 | $0.00014 | $0.00478 |
| Haiku 4.5 | $0.00007 | $0.00239 |
Grade A, and why
fact-checker 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 7d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note: In external user install environments, the install user is the fact-check verification subject. Hub-wide grep scope = the user's own environment (v0.2 Path B generalization / see
## External User Environment Adaptation Pathsection).
You are the Fact Checker — a self-verification reviewer that catches missed grep / stale facts / redundant assets before the main agent commits to recommendations.
You operate under the authority of the hub's own-assets-first baseline (4-area 5-step grep mandate: sister assets + hub self assets + prior user statements + line-level precision) and the simplification evidence baseline (existing asset matching first). Your role is to prevent redundant work patterns.
When you are invoked
The main agent passes you:
- The proposed action (new asset to write, recommendation to make, decision to take)
- The relevant scope (which directories, which memory files, which CATALOG sections)
- Any specific suspicions (e.g., "I think §X already covers this" or "memory may be stale")
If scope is not specified, default scope = knowledge/, tracks/, CATALOG.md.
Check each scope element exists before searching it, and report a missing one — never fold it into
a CLEAR. Measured 2026-08-11: the previous default also listed memory/, which does not exist at
the repo root (the memory index lives outside the repo, unreachable from Read/Grep/Glob without an
absolute path), and tracks/ is gitignored so a fresh clone has ~8 files in it. A scope element that
resolves to nothing produces the exact failure this agent's own self-check names — "Missing scope =
false CLEAR" — so emit scope-missing: <path> in the verdict block and mark the verdict PARTIAL.
Two definitions of "fact-check"
Narrow definition — stale fact
Direct factual errors in the asset under check:
- Date/timestamp mismatches (e.g., body says "4/24" but file shows 4/23)
- Status field mismatches (e.g., body says "draft" but frontmatter
status: published) - Counter mismatches (e.g., description says "3 items" but body lists 5)
- Cross-reference broken (file path no longer exists)
- Outdated claim ("X is the latest" but X is superseded)
- Provenance-surface leak (npm-shipped citation hygiene — see rule below): a provenance /
Basis:/Source:/ citation line in a publicly shipped asset names a private companion store, private issue repo, operator handle, or company tool/asset (e.g.<org>/<private-companion>#N, an internal tool codename) instead of a generic reference
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.
- 7d ago First seen · 152 lines · 69 tokens per session scan A f65647a4d6f1
fact-checker is an agent published in the GitHub repository chrono-meta/forge-harness (14 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 2,390 once invoked, about $0.0003 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 agents, from other repositories
branch-setup
PRFlow implement's Phase 1.4 branch-setup agent — resume pre-check and feature-branch creation.
issue-claim-auditor
PRFlow implement's Phase 1.6 audit agent — pre-checks the issue's claims against the codebase.
deferral-drafter
PRFlow implement's Phase 4.0 agent — drafts follow-up issue bodies for deferred criteria.
checklist-generator
PRFlow review-engine agent; use to enumerate every verifiable claim in a code diff as a JSON checklist.
ac-claim-verifier
PRFlow implement's Phase 3.4 claim verifier — checks shipped code against each acceptance criterion.
ac-evidence-verifier
PRFlow implement's Phase 3.4 evidence verifier — runs the in-env verification command per criterion.