Borrowing it
Nothing to install: this file belongs to JustasMonkev/mcp-accessibility-scanner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JustasMonkev/mcp-accessibility-scanner/main/.codex/skills/pre-push-review/SKILL.mdgit clone --depth 1 https://github.com/JustasMonkev/mcp-accessibility-scannerWrote 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/justasmonkev/mcp-accessibility-scanner/pre-push-review)<a href="https://agentmods.dev/skills/justasmonkev/mcp-accessibility-scanner/pre-push-review"><img src="https://agentmods.dev/badge/skills/justasmonkev/mcp-accessibility-scanner/pre-push-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/justasmonkev/mcp-accessibility-scanner/pre-push-review"><img src="https://agentmods.dev/badge/skills/justasmonkev/mcp-accessibility-scanner/pre-push-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 | $0.00113 | $0.03351 |
| Opus 5 | $0.00056 | $0.01675 |
| Sonnet 5 | $0.00023 | $0.00670 |
| Haiku 4.5 | $0.00011 | $0.00335 |
Grade A, and why
pre-push-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 12d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-push review: catch Codex findings before they reach GitHub
This repo's PRs are reviewed by the OpenAI Codex bot. An analysis of all 179 inline findings it left across ~50 PRs shows the same defect classes recurring again and again. Almost every one of them was detectable from the diff alone — which means you can catch them locally.
Work through the checklist below against your actual diff — everything that differs from the default branch (git diff origin/main...HEAD, or git diff main...HEAD in a checkout with no origin remote; if neither ref exists, diff against the merge base of whatever ref tracks the default branch) plus any staged and unstaged changes. Don't treat it as a form to tick off: for each section, ask "does my change touch this territory?" — if yes, actively hunt for the failure mode described. Fix what you find, then run the final gate.
For concrete examples of every pattern (real findings with file/PR references), read references/codex-findings-catalog.md. Consult it whenever a section below feels abstract or you want to see what the failure looks like in practice.
1. Trace every option end-to-end — no silent no-ops
The single most common Codex finding (~20 occurrences): a flag, config field, or env var is accepted but silently ignored on some code path. --storage-state validated at startup but dropped by the VS Code/extension/CDP context factories; --mobile accepted with remoteEndpoint/cdpLaunch/--extension where context options are never applied; a configurable timeout that the SDK's own default overrides; a progress token forwarded but notifications never bridged through the proxy backend.
If your change adds or touches any option, setting, or env var:
- Enumerate every consumer path: launch modes (persistent,
--isolated,remoteEndpoint,cdpEndpoint,cdpLaunch,--extension,--vscode), transports (stdio, HTTP), and the proxy backend. Grep for where the value is read. - For each path, the option must be either applied or rejected with a clear error at startup. "Accepted but ignored" is never acceptable — the user believes they got the behavior (e.g. runs an "authenticated" audit that is actually anonymous).
- Validate against the merged config (CLI + config file + env), not just
cliOptions— Codex caught mobile validation that only inspected the CLI flag while the config file smuggled in a CDP endpoint. - Check the value is honored at runtime too: does a later runtime update (e.g.
browser_default_timeout) actually reach the code that reads the config snapshot? - Env var parsing: a present-but-blank value must not become
0/{}and change semantics (blankPING_TIMEOUTdisabled the heartbeat entirely). Values containing commas/colons must survive parsing (comma-splitting broke comma-valued headers). - Consistency between what you advertise and what you enforce: the server printed a
0.0.0.0URL that its own Host-header allowlist then rejected with 403.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 140 lines · 113 tokens per session scan A 1ae1f824cfbb
pre-push-review is a skill published in the GitHub repository JustasMonkev/mcp-accessibility-scanner (56 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 3,351 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…