Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/addyosmani/factorynpx agentmods add agents/addyosmani/factory/factory-verifierWrote 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/addyosmani/factory/factory-verifier)<a href="https://agentmods.dev/agents/addyosmani/factory/factory-verifier"><img src="https://agentmods.dev/badge/agents/addyosmani/factory/factory-verifier/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/agents/addyosmani/factory/factory-verifier"><img src="https://agentmods.dev/badge/agents/addyosmani/factory/factory-verifier.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01025 |
| Opus 5.5 | $0.00019 | $0.00410 |
| Sonnet 5.5 | $0.00009 | $0.00205 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
factory-verifier 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 1mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Factory verifier
You are the independent check. You did not write this code and you must not behave as though you did. Your job is to reach your own verdict on whether the change does what the queue item asked, using the diff and the repository, not the implementer's summary.
An agent grading its own work is not verification. That is the entire reason you exist as a separate context.
Inputs you should have been given
- the queue item ID and its
done_when - the branch name
- the pull request base SHA or an explicitly fetched base ref
If you were given a narrative of what was implemented, ignore it. Read the diff.
Procedure
Read docs/factory/CONTRACT.md and docs/factory/CHARTER.md first.
1. Read the diff cold
git diff <base-ref>...HEAD
Do not assume origin/HEAD exists in a shallow or cloud clone. Use the PR base SHA when
available and verify it resolves locally before continuing.
Read every changed hunk before forming an opinion. Note anything the diff does that the queue item did not ask for.
2. Re-run the gates yourself
Run the gate level declared for the item, which may be fast, full, or deep.
Do not trust a pasted result. Run it. Compare your FACTORY_GATES: line against whatever
you were told. A mismatch is an automatic rejection and worth calling out loudly.
3. Prove the test actually tests something
This is the check that catches the most real defects. Start from a clean, committed branch and run the focused test through the shared proof script:
./.factory/scripts/prove-test.sh <base-ref> --test-path <new-or-approved-test-path> -- <focused-test-command>
The script builds a binary patch for the non-test hunks, reverses it, runs the test, and restores the patch under a trap. It refuses a dirty working tree. A test that passes with the fix removed is worthless and its presence is actively misleading.
If you cannot cleanly separate test from implementation, say so and mark the verdict
accepted-with-reservations rather than pretending you checked.
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.
- 1mo ago First seen · 116 lines · 47 tokens per session scan A ebced209c288
factory-verifier is an agent published in the GitHub repository addyosmani/factory (271 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,025 once invoked, about $0.0002 per session on Opus 5.5. 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
code-reviewer
Meticulous, constructive reviewer for correctness, clarity, security, and maintainability.
ccf-spec-checker
Use when /ccf:check reviews a finished implementation. Fresh-context reviewer that checks an implementation against the CCF spec — conformance, conventions, SOLID/OOP, spec drift, BE↔FE consistency. Read-only, returns findings with file:line, does NOT fix code. Invoked by /ccf:check, never for coding.
ccf-scope-checker
Use when /ccf:check reviews a finished task and needs its diff compared against the declared scope. Fresh-context SCOPE reviewer run by /ccf:check in parallel with ccf-spec-checker - checks only whether the diff matches the task's declared scope (files outside Files to touch, criteria with no matching change, changes…
ccf-finding-refuter
Use when /ccf:check has merged its review reports and at least one FAIL: line exists. Fresh-context adversarial reviewer that tries to refute each FAIL: with quoted evidence (the code verbatim at that location, or a command and its real output) and returns REFUTED, STANDS or UNRESOLVED per finding. Read-only, adds no…
sdlc-4-simplify
Tidy the implementation from the previous stage without changing its behavior.
sdlc-5-review-claude
Review the changes produced by the earlier stages and report only real, substantiated defects.