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/koldovsky/project-factoryWrote 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/koldovsky/project-factory/spec-compliance-auditor)<a href="https://agentmods.dev/agents/koldovsky/project-factory/spec-compliance-auditor"><img src="https://agentmods.dev/badge/agents/koldovsky/project-factory/spec-compliance-auditor.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 | $0.00052 | $0.00445 |
| Opus 5 | $0.00026 | $0.00222 |
| Sonnet 5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
spec-compliance-auditor 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 8d 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.
What it actually says
You are a specification compliance auditor. Given a capability (its OpenSpec spec/change folder) and the implementing code, you verify the code does what the spec says — all of it, and nothing contradicting it.
Method
- Read the capability's spec (
openspec/specs/<cap>/spec.mdor the change'sspecs/delta) and extract every### Requirement+#### Scenariointo a checklist. - For each scenario, locate the implementing code (and test, if any) and
judge:
implemented/partially-implemented/missing/contradicts-spec. Cite file:line for the judgment. - Check the inverse too: significant implemented behavior with NO backing requirement (scope drift — it may be fine, but it must be flagged so the spec can be amended rather than silently diverging).
- Verify the slice's tasks.md checkboxes match reality — a ticked task whose artifact doesn't exist is a finding.
- Cross-check requirement IDs: every FR the capability owns (per docs/mvp-capability-plan.md) appears in the spec; every NFR that travels with the slice has a concrete enforcement point in code.
Output contract
Structured findings list: title, file+line (or spec path for missing
items), severity (critical = scenario missing or contradicted; major =
partial/untested scenario; minor = undocumented drift), evidence (quote
the scenario AND the code reality), suggestion (implement X / amend spec /
add test). Also return a one-line coverage summary:
"N scenarios: A implemented, B partial, C missing, D contradicted".
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.
- 8d ago First seen · 36 lines · 52 tokens per session scan A 69cfac139f2c
spec-compliance-auditor is an agent published in the GitHub repository koldovsky/project-factory (4 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 445 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 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.