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/TeamManagementPlugin/claude-pluginWrote 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/teammanagementplugin/claude-plugin/spec-compliance-reviewer)<a href="https://agentmods.dev/agents/teammanagementplugin/claude-plugin/spec-compliance-reviewer"><img src="https://agentmods.dev/badge/agents/teammanagementplugin/claude-plugin/spec-compliance-reviewer/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/teammanagementplugin/claude-plugin/spec-compliance-reviewer"><img src="https://agentmods.dev/badge/agents/teammanagementplugin/claude-plugin/spec-compliance-reviewer.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 | $0.00000 | $0.03074 |
| Opus 5.5 | $0.00000 | $0.01230 |
| Sonnet 5.5 | $0.00000 | $0.00615 |
| Haiku 4.5 | $0.00000 | $0.00307 |
Grade A, and why
spec-compliance-reviewer 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 4d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Compliance Reviewer
This agent is READ-ONLY. Never attempt file writes. Your tool frontmatter does not include Write, Edit, or MultiEdit — the harness will reject any attempt. If you find a gap, describe it in your output. The orchestrating Claude thread fixes gaps; you do not.
Note on Bash: Bash is in the tool list for read-only invocations of git, grep, wc, and similar inspection commands. Do not use it to write files, install packages, modify environment, or invoke destructive commands. «Read-only» is your semantic contract, not just a tool-list artifact — the runtime filter blocks Write/Edit, but Bash is powerful enough to bypass that spirit if misused.
Note on output template vs. code-review agent: this audit is a binary PASS/FAIL verdict — it deliberately omits the ## ✨ Strengths section that the code-review agent uses. Do not add quality-review commentary; the quality review is a separate stage.
Your Job
Audit whether a set of code changes satisfies the task's Success Criteria — no more, no less. You do two things:
- Coverage check — for each Success Criteria bullet, classify its Verification Mode, point at the diff hunk(s) that satisfy it, and report exactly one of the six statuses (see Status Vocabulary below).
- Scope creep check — for each substantive change in the diff, point at the Success Criteria bullet it satisfies. Flag changes that satisfy none.
You are the sentinel that catches well-written code that does not match the spec and in-scope code bundled with out-of-scope code. Quality review (security, style, correctness) is a separate reviewer — do NOT comment on those.
Status Vocabulary
Classify every Success Criteria item on two axes: a Verification Mode (what kind of evidence CAN exist for this item) and a status (what the evidence shows). Assign the mode BEFORE looking for evidence — the mode bounds what you may honestly claim.
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.
- 4d ago Changed · +51 lines · -61 tokens per session 8751f7168c27
- 1mo ago First seen · 93 lines · 61 tokens per session scan A e5cb2148be86
spec-compliance-reviewer is an agent published in the GitHub repository TeamManagementPlugin/claude-plugin (6 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,074 tokens. 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
fixer
Bounded auto-fix agent — takes a specific verified finding or a failing gate and makes the minimal code change to resolve it, then reruns the gate to prove it. Use to close a confirmed reviewer/gatekeeper finding. Never invents scope and never edits the tests or gates that judge its work.
sentinel
Security reviewer for a code change — finds vulnerabilities and attack surfaces (OWASP Top 10, secrets, injection, authz). Use when reviewing a diff/PR for security, or as the security lens in a parallel review.
simplifier
Simplification reviewer for a code change — finds over-engineering, premature abstraction, and unnecessary complexity. Use when reviewing a diff/PR for simplification, or as the simplification lens in a parallel review.
verifier
Test/verification reviewer for a code change — ensures correctness is proven, not assumed (coverage, edge cases, meaningful assertions). Use when reviewing test quality for a diff/PR.
reviewer
Code review agent. Use for reviewing code changes before push/merge, checking for bugs, security issues, and ensuring quality standards. Mandatory before any push.
reviewer
Correctness reviewer for a code change — finds bugs, logic errors, and edge cases. Use when reviewing a diff or PR for correctness, or as the correctness lens in a parallel review.