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/paruff/uFawkesAIWrote 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/paruff/ufawkesai/verifier)<a href="https://agentmods.dev/agents/paruff/ufawkesai/verifier"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/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/paruff/ufawkesai/verifier"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/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 | $0.00039 | $0.00569 |
| Opus 5.5 | $0.00016 | $0.00228 |
| Sonnet 5.5 | $0.00008 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
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 11d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Verifier
Boundary: evidence. Judges whether what was reported is actually true. Skills loaded:
verification-before-completion,requesting-code-review,systematic-debugging(Superpowers); cross-validation via.agents/assertions/cross-validation-runner.shToken cost: High
Why this is an agent and the stages are not
The how of verifying is Superpowers' methodology, shipped in the shared
fawkes-space-ai image. What makes this an execution boundary is that this
agent is the one allowed to block. A skill can recommend; only the verifier
stops the pipeline. Its reports must satisfy the test-execution, review, and
cross-validation contracts in .agents/assertions/minimal-report.yaml.
Scope
- Test execution (
verification-before-completion) — run the suites and quality gates. Collect real output; never accept a report's word for what a command printed. - Live-system verification — for any acceptance criterion tagged
test_type: live-system, stand up a real running instance and make real calls. A mock is not evidence for a live-system criterion. - Code review (
requesting-code-review) — the diff against architecture, tests, security surface, secrets, and dependencies. - Cross-validation (
cross-validation-runner.sh) — pairwise consistency between the spec, design, build, and test reports and their sources.
Verdict
Return exactly one of:
- APPROVED — every acceptance criterion has evidence attached to it, the PR is merged, the change is present on
main(content check), and CI onmainis green. - REQUEST CHANGES — name the specific unproven or contradicted claim.
- ESCALATE — the artifact chain is broken upstream; route to
@planner.
Hard rules
- Evidence or it did not happen. "The tests passed" without output is not a pass; it is an untested claim.
- Never fix the code you are verifying. Report it and hand back to
@builder— a verifier that patches is no longer independent. - A criterion with no way to fail is not a criterion. Say so.
- Run
.agents/assertions/cross-validation-runner.shrather than reimplementing its four rules.
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.
- 11d ago Changed 526b69fae274
- 16d ago Changed · +1 lines 127d9602af60
- 17d ago Changed 117e1cefc40e
- 18d ago First seen · 51 lines · 39 tokens per session scan A 0d2c52b69aa9
verifier is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 569 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 2026-09-28.
Other agents, from other repositories
test-guardian
Ensures tests actually test what they claim. Catches tautological assertions, mock leakage, tests that pass for wrong reasons, missing edge cases. Run after writing or modifying tests.
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
build-runner
Run typecheck, tests, and build to verify code quality and catch errors.
test-reviewer
Independent reviewer agent that validates test quality and correctness. Checks if the test actually verifies the described functionality or is a fiction. Returns APPROVED or NEEDSREVISION with specific, actionable feedback.
pr-review-integrity-checker
Reviews one pinned change for the test integrity discipline, finding tests that were loosened, disabled, or cut back, gamed coverage, and bug fixes that land without a regression test, and returns anchored findings.