coder-self-review

coder-self-review is a skill for Claude Code, Codex from ntorga/agent-starter-kit. It costs 24 tokens per session (2,199 once invoked), scanned A, original, MIT.

A self-review rubric for a coding helper. It evaluates a completed handoff against defined criteria and evidence from the actual work.

In plain words
What is it for?
It helps verify changed files, run tests, inspect suppressions and placeholders, check for secrets, and assess exposed input paths.
Why use it?
It helps catch unfinished markers, failing tests, unjustified lint exceptions, exposed secrets, and other delivery problems before handoff.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps verify changed files, run tests, inspect suppressions and placeholders, check for secrets, and assess exposed input paths.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ntorga/agent-starter-kit/coder-self-review
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.

Any agent
npx skills add ntorga/agent-starter-kit --skill coder-self-review
Clone the repo
git clone --depth 1 https://github.com/ntorga/agent-starter-kit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for coder-self-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/coder-self-review/github.svg)](https://agentmods.dev/skills/ntorga/agent-starter-kit/coder-self-review)
Your own site
<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/coder-self-review"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/coder-self-review/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.

agentmods 80×15 button for coder-self-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/coder-self-review"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/coder-self-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,199 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00024 $0.02199
Opus 5 $0.00012 $0.01099
Sonnet 5 $0.00005 $0.00440
Haiku 4.5 $0.00002 $0.00220

Measured 2d ago against content hash 26e830f31835, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-14, from the pricing page.

Security

Grade A, and why

coder-self-review 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 2d 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.

skills/coder-self-review/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Before delivering a handoff, the Coder evaluates its own output against the GRASP rubric. Each letter is scored 0, 1, or 2 with evidence quoted from the rubric and cited from actual work. The total determines whether to deliver, rewrite, or abort.

Procedure

  1. Gather evidence. Honest self-review makes verification efficient. Accurate scorecards confirm fast; dishonest ones fail and re-run, wasting time and compute. Before scoring, run verification commands to gather proof. The examples below show common patterns — choose what provides the best evidence for your specific work.

    Examples:

    • Incomplete markers: rg -n 'TODO|FIXME|HACK|stub|placeholder' <changed-files> — zero results supports higher scores
    • Test suite: run the project's test command — all passing supports higher scores
    • Lint suppressions: rg -n 'nolint|eslint-disable|@ts-ignore|# noqa|disable-line' <changed-files> — zero results or justified suppressions support higher scores
    • Secrets: rg -n 'password|secret|api_key|token|PRIVATE.KEY' <changed-files> — zero results in source supports higher scores
    • Attack surface: identify every endpoint/handler accepting external input — verify each has explicit auth and input sanitization
    • Run the project's linter if one exists.

    These are examples, not mandates. Choose commands that provide the strongest proof for your work.

  2. Score each criterion. Read the GRASP rubric below. For each letter, assign a score of 0, 1, or 2. You must:

    • Quote the specific criterion level (0, 1, or 2) that your work matches.
    • Cite evidence from your actual work — file paths read, commands run, test output, patterns checked. Generic claims like "I followed all guidelines" are not evidence and score 0.
  3. Output the Scorecard. Fill in the scorecard below. This is not internal reasoning — this is your deliverable checkpoint.

  4. Apply the hard-fail rule. If any letter scores 0, do not deliver — go to step 5 immediately.

Read the full file on GitHub · 110 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. 2d ago First seen · 110 lines · 24 tokens per session scan A 26e830f31835

Subscribe to this mod's changes

coder-self-review is a skill published in the GitHub repository ntorga/agent-starter-kit (142 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 2,199 once invoked, about $0.0001 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 2026-09-13.