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 yannmenec/inspectrum --skill review-plan-with-claudegit clone --depth 1 https://github.com/yannmenec/inspectrumWrote 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/yannmenec/inspectrum/review-plan-with-claude)<a href="https://agentmods.dev/skills/yannmenec/inspectrum/review-plan-with-claude"><img src="https://agentmods.dev/badge/skills/yannmenec/inspectrum/review-plan-with-claude/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/yannmenec/inspectrum/review-plan-with-claude"><img src="https://agentmods.dev/badge/skills/yannmenec/inspectrum/review-plan-with-claude.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 | $0.00050 | $0.00383 |
| Opus 5 | $0.00025 | $0.00192 |
| Sonnet 5 | $0.00010 | $0.00077 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
review-plan-with-claude 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.
What it actually says
Review a Codex plan with Claude
Use the most recent complete development plan visible in the conversation. If there is no complete plan, ask the user for it instead of inventing missing steps.
Call only mcp__inspectrum__review_plan, once, with:
plan: <the full plan in Markdown>
reviewers: ["claude"]
focus: all
judge: false
Keep an explicitly requested focus (correctness, completeness, risk, or
clarity) instead of all. Do not add another reviewer, invoke a judge, call a
second tool, or substitute Codex's own analysis for Claude's review.
Successful result
Treat the review as successful only when the tool response does not have
isError: true and includes structuredContent with verdict and
report_markdown.
Render report_markdown, identify the verdict as Claude's review, and include
the session path. If a revised_plan is present, offer it to the user without
executing it or silently replacing the original plan.
Claude or tool unavailable
If the call fails, returns isError: true, or has no valid
structuredContent, say:
The Claude review did not complete.
Show the concise, non-sensitive error text when available. Suggest checking
claude --version, completing Claude's interactive authentication, and then
retrying the review. Never present this failure as approve, as a successful
review, or as an opinion actually produced by Claude.
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 · 46 lines · 50 tokens per session scan A e110a245a8a9
review-plan-with-claude is a skill published in the GitHub repository yannmenec/inspectrum (2 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 383 once invoked, about $0.0003 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
nopus-configure
Configure nopus complexity sensitivity, extra-simple rewrites, rewrite evidence, and Pi response hiding for this user.
dvalin-security-scan
Scan code for injection, hardcoded secrets, XSS, dynamic code execution, and unsafe shell use. Use after writing or modifying code that handles user input, builds queries or commands, touches authentication, or adds a dependency — and whenever the user asks for a security check, audit, or review. Runs locally with no…
coding-agents-farm
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
nopus-simplify
Rewrite the immediately preceding assistant response with clearer and more direct prose when the user invokes this skill.
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…
odds-api
Build custom apps, bots, dashboards, scanners, and MCP workflows using Odds API data access.