review-spec-implementation

Review implementation against spec and document findings for fixes.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/jnarowski/agentcmd/review-spec-implementation
Clone the repo
git clone --depth 1 https://github.com/jnarowski/agentcmd

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,740 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00009 $0.03740
Opus 5 $0.00005 $0.01870
Sonnet 5 $0.00002 $0.00748
Haiku 4.5 $0.00001 $0.00374

Measured today against content hash 049ec18d5672, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-spec-implementation 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 today.

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.

.claude/commands/cmd/review-spec-implementation.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Spec Implementation

Reviews a previous agent's implementation work by comparing the provided spec file against actual code changes. Identifies discrepancies and documents all findings in a Review Findings section appended to the spec. The documented issues can then be addressed by running /cmd:implement-spec on the updated spec file.

Variables

  • $specIdOrNameOrPath: $1 (required) - Either a timestamp ID (e.g., 251024120101), feature name (e.g., workflow-safety), or full path
  • $format: $2 (optional) - Output format: "text" or "json" (defaults to "text" if not provided)
  • $max-reviews: 3 - This is a constant (maximum review iterations allowed)

Spec File Resolution

Parse and resolve $specIdOrNameOrPath:

  • If it's a full path (contains /): use as-is
  • Otherwise, look up in .agent/specs/index.json:
    • For timestamp ID: Match by id field
    • For feature name: Fuzzy match path (e.g., message-queue matches todo/251024120101-message-queue-implementation/spec.md)
    • Use path from index: .agent/specs/{path}
  • If not found in index.json, fallback to directory search:
    • Search in order: backlog/, todo/, done/
    • For ID: Pattern {id}-*/spec.md
    • For feature name: Pattern *{feature-name}*/spec.md (fuzzy match)
  • If still not found: stop and report error

Instructions

  • REVIEW ONLY - This command does not implement fixes
  • Evidence-based - Every finding must cite file:line and quote spec requirements
  • Priority-focused - Only document HIGH and MEDIUM priority issues (see guidelines below)
  • Pragmatic mindset - Ask "would this block a PR merge?" not "could this be better?"
  • Project standards - Check .agent/docs/code-review-standards.md for detailed review methodology. If that file is missing, look for best practices in CLAUDE.MD
  • Maximum Iterations: Reviews stop automatically after 3 iterations
  • Act as a professional code auditor, not a nitpicking perfectionist
  • If $format is not provided, default to "text"

Read the full file on GitHub · 411 lines

Changes

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.

  1. today First seen · 411 lines · 9 tokens per session scan A 049ec18d5672

Subscribe to this mod's changes

review-spec-implementation is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 9 tokens to every session and 3,740 once invoked, about $0.0000 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 2026-09-01.