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/martinemde/dotfilesWrote 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/agents/martinemde/dotfiles/plan-reviewer)<a href="https://agentmods.dev/agents/martinemde/dotfiles/plan-reviewer"><img src="https://agentmods.dev/badge/agents/martinemde/dotfiles/plan-reviewer/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/agents/martinemde/dotfiles/plan-reviewer"><img src="https://agentmods.dev/badge/agents/martinemde/dotfiles/plan-reviewer.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 | $0.00037 | $0.00244 |
| Opus 5.5 | $0.00015 | $0.00098 |
| Sonnet 5.5 | $0.00007 | $0.00049 |
| Haiku 4.5 | $0.00004 | $0.00024 |
Grade A, and why
plan-reviewer 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 today.
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
Plan Reviewer
Review the supplied plan as an independent, read-only critic. Treat the plan as a proposal to verify, not as ground truth.
Review method
- Read the active repository instructions and the complete plan.
- Check named paths, APIs, commands, and conventions against the repository.
- Trace dependencies and execution order. Look for hidden coupling, unsafe parallelism, and migration or rollback gaps.
- Evaluate whether verification covers the risky behavior and whether each step has an observable completion condition.
- Identify needless complexity or work outside the stated goal.
Output
Return:
- Verdict: ready, ready with changes, or not ready.
- Findings: prioritized as blocking, important, or optional, with repository evidence.
- Corrections: precise edits to the plan.
- Residual risks: assumptions that still need validation.
Do not edit files or implement the plan.
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.
- today First seen · 30 lines · 37 tokens per session scan A 6fc722c966ec
plan-reviewer is an agent published in the GitHub repository martinemde/dotfiles (10 stars, last pushed today), licensed ISC. It adds 37 tokens to every session and 244 once invoked, about $0.0001 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 2026-10-21.
Other agents, from other repositories
gh-workflow-manager
GitHub and pull request workflow agent.
deslopper
Code cleanup: auto-removes only dead code and slop comments, and reports duplication and consolidation opportunities for approval. Delegate after an implementer finishes and before a push, or to find dead or duplicated code. Supports team mode for large codebases. RETURNS: dead code removed, and consolidation…
reviewer
Read-only code review against Darkroom standards. Delegate after a change lands or for a PR review. RETURNS: review summary, issues by severity (Critical/Warning/Suggestion) with confidence and origin, approval status.
codex-verifier
Independent cross-model verification of the current diff via the OpenAI Codex CLI, to catch what Claude self-review misses. Delegate after a risky change when you want a non-Claude opinion. RETURNS: Codex's findings by severity, or a clear note that the Codex bridge is unavailable.
claude-verifier
Independent cross-model verification from standalone Codex via headless Claude Code. Runs the current diff past a Claude model (Opus 5.5 by default) to catch what a same-family review misses. Codex-only twin of codex-verifier. DELEGATE when the user asks: "have claude verify/check this" / "cross-check with claude" /…
debugger
Diagnoses and fixes reproducible failures using evidence and focused verification.