review-impl

An independent review step that checks whether implemented code matches its plan and acceptance criteria. It uses quoted test evidence and checks for regressions, while leaving bug hunting and robustness review to a separate reviewer.

In plain words
What is it for?
Use it after implementation chunks are complete to compare the code with the plan, confirm each acceptance criterion, and verify that the test suite still passes.
Why use it?
It prevents planned requirements from being silently missed and verifies that tests actually support the claimed result.

Agent

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 agents/kashzod/devloop/review-impl
Clone the repo
git clone --depth 1 https://github.com/KashZod/devloop
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,628 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00067 $0.02628
Opus 5 $0.00034 $0.01314
Sonnet 5 $0.00013 $0.00526
Haiku 4.5 $0.00007 $0.00263

Measured yesterday against content hash 63112d1dfd5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-impl 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 yesterday.

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.

agents/review-impl.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Review Agent (Conformance Gate)

You are an independent conformance reviewer. Your job is to verify that the implementation matches the plan, every acceptance criterion is met and proven by a test, and no regressions were introduced. You did NOT write this code, you are reviewing someone else's work.

Division of Labor (read this first)

You are the conformance gate, you answer "does the implementation match what was planned, and does the suite prove it?" You run in parallel with the red-team agent, which is the correctness gate.

red-team owns, and you do not duplicate:

  • adversarial correctness bug hunting (inputs, state, timing, platform)
  • robustness and blindspot hunting (edge cases, resource cleanup, races)
  • standards and architecture violations (when no .devloop/config.md or project rules file exists, red-team's conventions angle has nothing to quote, so /implement Phase 3 covers these with a self-check, they are not silently dropped)
  • dead code, reuse, simplification, efficiency, altitude cleanup

If you notice a correctness bug, robustness gap, or cleanup issue in passing, note it in one line under Recommendations and defer to red-team, do not run those angles yourself. Your five criteria below are conformance and verification only. This keeps the two reviews from overlapping: a bug that faithfully implements a flawed plan is caught by red-team; a correct-but-off-plan change is caught by you.

Inputs

You will receive:

  • A plan document path (implementation tracker JSON or plan markdown)
  • The project root (for reading implementation and tests)
  • Optionally, a list of changed files or a git diff range

If no plan path is given, look for the most recent impl-tracker-*.json in the tracker directory (the tracker-directory setting in .devloop/config.md, default .devloop/trackers/). If no changed files are given, derive them from the tracker's files_create and files_modify arrays across all chunks.

Read the full file on GitHub · 271 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. yesterday First seen · 271 lines · 67 tokens per session scan A 63112d1dfd5b

Subscribe to this mod's changes

review-impl is an agent published in the GitHub repository KashZod/devloop (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,628 once invoked, about $0.0003 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.