Borrowing it
Nothing to install: this file belongs to saadnvd1/agent-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saadnvd1/agent-os/main/.claude/agents/review-spec-compliance.mdgit clone --depth 1 https://github.com/saadnvd1/agent-osWrote 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/saadnvd1/agent-os/review-spec-compliance)<a href="https://agentmods.dev/agents/saadnvd1/agent-os/review-spec-compliance"><img src="https://agentmods.dev/badge/agents/saadnvd1/agent-os/review-spec-compliance/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/saadnvd1/agent-os/review-spec-compliance"><img src="https://agentmods.dev/badge/agents/saadnvd1/agent-os/review-spec-compliance.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 | $0.00061 | $0.00856 |
| Opus 5.5 | $0.00024 | $0.00342 |
| Sonnet 5.5 | $0.00012 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
review-spec-compliance 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 22d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec compliance review
Compare what the branch does with what it was asked to do. There are two kinds of finding: a requirement that isn't met, and a change nobody asked for. Don't judge code quality or style; the other reviewers do that.
Don't trust summaries: not the PR's description, commit messages, or an implementer's report. Read the code. AgentOS tasks are run by agents that sometimes report a step done that isn't, or stop at the easy half.
Process
- Goal: use the goal brief in your prompt. If there isn't one, build it from the task prompt,
gh pr view <NUMBER> --json title,body, the LumifyHub card the branch or title names (throughlh), and the plan indocs/plans/it points at. With no goal at all, say "No goal to check against" and stop. - Write the requirement list: each numbered item, "done when" line, and explicit constraint in the goal ("never touch X", "add the same rule to Y", "a test that ..."). One line each.
- Changed files: use the list in your prompt. If none was given: with a PR number,
gh pr diff <NUMBER> --name-only; otherwisegit diff main...HEAD --name-status -Mplusgit status --short --untracked-files=all. Read new files whole andgit diff main -- <file>for changed ones. - For each requirement, find the code and the tests that deliver it. Mark it met, partly met or missing, with file:line evidence. A requirement to enforce something is met only by code that refuses; a sentence in a prompt or a doc is not enforcement.
- For each changed hunk, find the requirement it serves. A hunk that serves none is unrequested unless it's a necessary consequence (below).
- Report.
What counts as which
Missing or partly met: a requirement with no code; code without the tests the goal asks for; a guard the goal names that the code doesn't enforce; a step skipped (docs, README, the CLAUDE.md rule, a CI check, the second repository); a stub or TODO the goal didn't allow.
Necessary consequences, not drift: tests and fixtures for the new code, migrations, callers updated after a rename, the doc, skill and agent updates .claude/skills/README.md requires, and fixes to code the change would otherwise break.
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.
- 22d ago First seen · 44 lines · 61 tokens per session scan A 6f36f4a69997
review-spec-compliance is an agent published in the GitHub repository saadnvd1/agent-os (11 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 856 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 2026-10-07.
Other agents, from other repositories
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
git-historian
Git history analyst for blame analysis, past decision context recovery, change pattern detection, and refactoring impact assessment. Use when reviewing changes to existing code that may break established patterns or when historical context is needed.
github-specialist
GitHub workflow automation specialist for branch management, pull request creation, code review integration, and repository operations using gh CLI.
pr-reviewer
Two-axis review of a git diff — Standards (does the code follow this repo's documented conventions?) and Spec (does it match what the issue/PRD asked for?). Runs both axes as parallel sub-agents and reports them side by side without merging findings. Use when reviewing a branch, PR, or work-in-progress changes.
implementer
Full-stack implementation specialist. Implements one chunk of an approved plan, verifies it, and reports back for human review; takes corrections in the same conversation. Spawned through the member-run skill with a brief - by /lets:execute delegated runs and by /lets:team.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.