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.
npx skills add tomzx/agents --skill session-reviewgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/skills/tomzx/agents/session-review)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.02014 |
| Opus 5 | $0.00020 | $0.01007 |
| Sonnet 5 | $0.00008 | $0.00403 |
| Haiku 4.5 | $0.00004 | $0.00201 |
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.
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.
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.
- 7d ago First seen · 220 lines · 41 tokens per session scan A 27cfbc1b52aa
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.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.