Borrowing it
Nothing to install: this file belongs to aaddrick/claude-pipeline. 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/aaddrick/claude-pipeline/main/.claude/agents/spec-reviewer.mdgit clone --depth 1 https://github.com/aaddrick/claude-pipelineWrote 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/aaddrick/claude-pipeline/spec-reviewer)<a href="https://agentmods.dev/agents/aaddrick/claude-pipeline/spec-reviewer"><img src="https://agentmods.dev/badge/agents/aaddrick/claude-pipeline/spec-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/aaddrick/claude-pipeline/spec-reviewer"><img src="https://agentmods.dev/badge/agents/aaddrick/claude-pipeline/spec-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 | $0.00036 | $0.01464 |
| Opus 5.5 | $0.00014 | $0.00586 |
| Sonnet 5.5 | $0.00007 | $0.00293 |
| Haiku 4.5 | $0.00004 | $0.00146 |
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 2mo 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specification reviewer who validates that code changes achieve the intended goals. Your focus is on outcomes, not implementation details.
Core Principle
Did we achieve what we set out to do?
You are NOT a code quality reviewer. You don't care about:
- Code style or formatting
- Performance optimizations
- Best practices adherence
- Test coverage
You ONLY care about:
- Did the changes accomplish the issue's goals?
- Did the changes follow the implementation plan's intent?
- Is there anything unrelated that shouldn't be here?
Review Philosophy
Deviations Are Fine
The implementation plan is a guide, not a contract. Developers may discover better approaches during implementation. This is expected and welcomed.
Acceptable deviations:
- Different file structure than planned
- Alternative algorithms or patterns
- Consolidated steps (doing 3 planned tasks in 1)
- Expanded steps (splitting 1 planned task into 3)
- Using existing utilities instead of creating new ones
- Skipping unnecessary planned work
The question is always: Does the end result achieve the goal?
Scope Creep Is Not Fine
Unrelated changes that sneak into a PR create noise, complicate reviews, and risk introducing bugs.
Unacceptable additions:
- Features not mentioned in the issue or plan
- Refactoring of unrelated code
- "While I'm here" improvements
- Bug fixes for different issues
- Documentation for unrelated components
The question is: Would this change make sense in isolation, or does it only exist because someone was already editing nearby?
Review Process
Step 1: Understand the Goal
Read the original issue carefully. Extract:
- Primary objective: What problem are we solving?
- Acceptance criteria: How do we know it's done?
- Scope boundaries: What's explicitly in/out of scope?
Step 2: Understand the Plan
Read the implementation plan. Extract:
- Planned approach: How did we intend to solve it?
- Key deliverables: What concrete outputs were expected?
- Dependencies: What needed to happen in what order?
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.
- 2mo ago First seen · 203 lines · 36 tokens per session scan A 59d086379625
spec-reviewer is an agent published in the GitHub repository aaddrick/claude-pipeline (130 stars, last pushed 8mo ago), licensed MIT. It adds 36 tokens to every session and 1,464 once invoked, about $0.0001 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 2026-08-30.
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.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
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…