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.
git 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/commands/yannmenec/inspectrum/review)<a href="https://agentmods.dev/commands/yannmenec/inspectrum/review"><img src="https://agentmods.dev/badge/commands/yannmenec/inspectrum/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/commands/yannmenec/inspectrum/review"><img src="https://agentmods.dev/badge/commands/yannmenec/inspectrum/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 | $0.00012 | $0.00324 |
| Opus 5.5 | $0.00005 | $0.00130 |
| Sonnet 5.5 | $0.00002 | $0.00065 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Take the plan under discussion (the most recent ExitPlanMode argument, the
current plan file, or the visible plan in this conversation) and call the
review_plan MCP tool (inspectrum) with:
plan: the full plan markdownreviewers: if$ARGUMENTSis non-empty, split on commas, trim each item, and pass as a string array (e.g.codex,gemini→["codex","gemini"]); otherwise omit the field to use the user's~/.inspectrum/config.tomldefaultsjudge:true
The tool returns structuredContent with the typed result (verdict,
report_markdown, findings, optional revised_plan, session_id, session_path).
Render report_markdown verbatim. If verdict === "revise" and
revised_plan is non-empty, ask: "Apply the revised plan?".
If the tool is not available, tell the user to register the MCP server:
claude mcp add --transport stdio --scope user inspectrum -- npx -y inspectrum@latest
Also recognize the natural-language trigger when the user types something like "review this plan with inspectrum" (with or without a reviewer list). Treat that as the same invocation as the slash command.
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.
- 1mo ago First seen · 28 lines · 12 tokens per session scan A 0b50d985c6ee
review is a command published in the GitHub repository yannmenec/inspectrum (2 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 324 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
plannotator-review
Open interactive code review for current changes, another directory, or a PR URL; --base / --diff-type pin the session's opening diff (session-only, git-only).
is-not-duplicated
please investigate the codebase based on your changes - do we have code duplication? After analysis, write updates to DUPLICATIONREPORT.md with the results. Keep in mind that other agents could keep their records, so you need to check the document first, decided to update or add new information.
review-pr
Command "review-pr" from saski/arnesto, covering review pr, what this command does, workflow steps, phase 0: initialize review and phase 1: analysis & summary.
review-code
Call getworkflowcommandguidance(kind="design-plan", focus="Architecture focus: inspect saved scripts against their current step objectives, input/output contracts, and relevant retained behavior. Propose improvements without applying them.
review
Comprehensive code review for blz changes.
implement
Multi-agent advisory squad workflow for implementing code changes: classify → score risk → select agents → planner → Gate 1 (plan approval) → advisory squad → Gate 2 (Blocker halt) → implementer → consolidator → verdict. Auto-detects depth (quick/normal/deep) from risk + file count; pass --quick or --deep to override.…