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 leviuszen/meaning-assurance --skill agent-reviewgit clone --depth 1 https://github.com/leviuszen/meaning-assuranceWrote 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/leviuszen/meaning-assurance/agent-review)<a href="https://agentmods.dev/skills/leviuszen/meaning-assurance/agent-review"><img src="https://agentmods.dev/badge/skills/leviuszen/meaning-assurance/agent-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/leviuszen/meaning-assurance/agent-review"><img src="https://agentmods.dev/badge/skills/leviuszen/meaning-assurance/agent-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00023 | $0.00360 |
| Opus 5 | $0.00012 | $0.00180 |
| Sonnet 5 | $0.00005 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
agent-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 10d 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.
What it actually says
Agent Review
Use this skill when Codex wants Claude Code, Reasonix, or a manual external agent to review work without taking over the main workspace.
Rules
- Prefer read-only review.
- Findings come before suggestions.
- Ask for file paths, line references, severity, and concrete risk.
- Optional fixes must be written as small suggestions or
patch.diff. - Codex decides whether findings are valid.
- For mandatory dual code or strategy review, use
New-AgentDiscussion.ps1 -AuditProfile scientific -Protocol adversarial-discussion -Agents claude-code,reasonix. While Reasonix is non-blocking, use-Agents claude-code -OptionalAgents reasonixand report that the audit is not dual when Reasonix is absent. - Round 1 is blind; Round 2 addresses only disputed, blocking, or weak-evidence findings.
- Do not treat Reasonix Desktop launch, instruction files, or single-reviewer completion as review evidence.
- Do not decide by model vote. Use
findings.json,disagreement-matrix.md, and verified calibration outcomes.
Review Packet Contents
Include:
- user request
- files or diff under review
- expected behavior
- tests already run
- tests still needed
- severity scale
- forbidden actions
Required Review Output
The external agent should write review.md with:
- Findings
- Evidence
- Suggested fixes
- Residual risks
- Tests recommended
For scientific review, use the finding block required by brief.md, including evidence, confidence, counter-evidence, blocking status, and a bounded recommended action.
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.
- 10d ago First seen · 45 lines · 23 tokens per session scan A ef3d57e9a4ff
agent-review is a skill published in the GitHub repository leviuszen/meaning-assurance (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 360 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 2026-08-31.
Other skills, from other repositories
orbit-github
Open Orbit briefing skill — selected by the Orbit pipeline when GitHub is the user's only connected connector, or when the user explicitly scopes their daily digest to GitHub. Pulls the past 24 hours of PRs, review requests, issues, CI runs, and merges from the user's authenticated GitHub connection and renders them…
diff-review
Render the patch-edit run's accumulated changes as a reviewable diff, surface it through a GenUI choice surface, and persist the user's accept / reject decision into the artifact manifest.
patch-edit
Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.
beautify-with-pingfusi
Beautify or redesign an existing website through iterative pingfusi review rounds with a real human reviewer. Use when asked to "beautify this website," "make this page look professional," "polish this UI/design," "improve the visual design," or finish an AI-built page when there is no reference site to match. Do not…
review-video-with-pingfusi
Have any video reviewed by a real human, through iterative pingfusi review rounds. Use when asked to "review this video", "check the rendered video", "does this video match the prompt/brief", "what do people think of this ad/trailer/demo", or after rendering a Remotion composition or AI-generated clip that no test can…