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.
npx agentmods add agents/shrekshrek/project-workflow/spec-reviewergit clone --depth 1 https://github.com/shrekshrek/project-workflowWrote 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/shrekshrek/project-workflow/spec-reviewer)<a href="https://agentmods.dev/agents/shrekshrek/project-workflow/spec-reviewer"><img src="https://agentmods.dev/badge/agents/shrekshrek/project-workflow/spec-reviewer.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 | $0.00042 | $0.00186 |
| Opus 5 | $0.00021 | $0.00093 |
| Sonnet 5 | $0.00008 | $0.00037 |
| Haiku 4.5 | $0.00004 | $0.00019 |
Grade A, and why
spec-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.
What it actually says
Response language: Match the calling user's language. Spec citations preserve source language. Code, commands, file paths, and file:line references stay as-is.
You are the Claude Code adapter for the canonical spec-reviewer.
Before reviewing, read:
${CLAUDE_PLUGIN_ROOT}/docs/reviewers/spec-reviewer.md(read completely; canonical contract)- the target feature's accepted
spec.mdand relevant optional design/work notes - changed implementation files in scope
Follow the canonical reviewer spec exactly. The accepted feature artifact is the baseline of truth. Do not make edits.
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 First seen · 18 lines · 42 tokens per session scan A 8d4924f37c8e
spec-reviewer is an agent published in the GitHub repository shrekshrek/project-workflow (2 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 186 once invoked, about $0.0002 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
arbiter
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
archon
Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across invocations. Does not write code — orchestrates those who do.
planner
Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.
reviewer
Read-only spec-compliance reviewer. Given a parent-assembled spec slice (the phase's plan section + task titles/notes + the named Architecture sections) and the just-built diff, returns a structured pass/fail verdict on whether the implementation matches the spec. Never writes. Invoked by /specmanager-build after the…
claude_science.zh
Claude Science 采用了更严格的沙箱（sandbox）策略，默认情况下无法读写主目录（）下的文件。这会导致通过常规方式配置的 MCP-for-Stata 服务端在启动时直接报错：.
qa-engineer
Writes cross-slice E2E tests covering flows that span multiple slices. Runs once after all feature slices complete in the Build phase. Reads implementation-log.md to understand the full shape of what was built. Flags which slices caused any E2E failures for targeted retry.