session-review

session-review is a skill for Claude Code, Codex from tomzx/agents. It costs 41 tokens per session (2,014 once invoked), scanned A, original, MIT.

A structured end-of-session checklist for reviewing recent code changes, tests, documentation, specifications, design choices, and follow-up risks.

In plain words
What is it for?
Use it to review a Git diff, check test and documentation coverage, assess architectural fit, and record newly discovered development practices.
Why use it?
It helps catch incomplete work, unnecessary complexity, breaking changes, rollback issues, and technical debt before the session ends.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it to review a Git diff, check test and documentation coverage, assess architectural fit, and record newly discovered development practices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/session-review
View source ↗ tomzx/agents
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 tomzx/agents --skill session-review
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

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 session-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/session-review/github.svg)](https://agentmods.dev/skills/tomzx/agents/session-review)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/session-review"><img src="https://agentmods.dev/badge/skills/tomzx/agents/session-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 session-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/session-review"><img src="https://agentmods.dev/badge/skills/tomzx/agents/session-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,014 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00041 $0.02014
Opus 5 $0.00020 $0.01007
Sonnet 5 $0.00008 $0.00403
Haiku 4.5 $0.00004 $0.00201

Measured 7d ago against content hash 27cfbc1b52aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

session-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 7d 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/session-review/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Review

Runs a structured end-of-session review to ensure every change made during the session is properly covered by tests, documented, specified, intentional, and as clean as possible. Also extracts and persists any newly identified practices.

Prerequisites

  • A git repository with changes from the current session
  • AGENTS.md present in the repository root (or a known location)
  • Spec files accessible (if the project uses specifications)

Steps

1. Collect the Intent Behind the Change

Review git diff HEAD~..HEAD (or all commits since the session started) and ask the user:

"What was the goal of this session? What problem were you solving, and what approach did you take?"

Record the stated intent. If the user does not respond, infer the intent from commit messages and changed code.

2. Simplicity Review

Before writing any tests or docs, review the changed code and ask:

"Could this be implemented more simply, cleanly, succinctly, or elegantly? Are there any abstractions that can be removed, renamed, or consolidated? Is there anything here that is over-engineered for what is actually needed?"

Apply any improvements the review surfaces. Tests, docs, and specs are written against this final, clean implementation.

3. Add Tests to Cover the Change

Identify all changed or added functions, classes, and modules. For each:

  • Check whether a test already exists that exercises the new or modified behavior.
  • If no test covers it, write one (or ask the user to confirm before writing).
  • Focus on "green path" tests that cover the main functionality.
  • Run the test suite to confirm all tests pass:
    # Python
    uv run pytest
    
    # JavaScript / TypeScript
    npm test
    
    # Go
    go test ./...
    
  • Report any failing tests and fix them before proceeding.

4. Update Documentation

For each changed public interface, module, or behavior:

  • Update inline docstrings or comments if the behavior changed.
  • Update any relevant README.md, docs/, or wiki pages.
  • If the project uses a changelog (CHANGELOG.md), add an entry under ## Unreleased.
  • If the project uses the Divio documentation system (tutorials, how-tos, reference, explanation), identify which document type needs updating and make the edit.

Read the full file on GitHub · 220 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. 7d ago First seen · 220 lines · 41 tokens per session scan A 27cfbc1b52aa

Subscribe to this mod's changes

session-review is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 2,014 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 2026-09-03.

Related

Other skills, from other repositories