Borrowing it
Nothing to install: this file belongs to mamertofabian/mcp-everything-search. 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/mamertofabian/mcp-everything-search/main/.claude/skills/maid-plan-review/SKILL.mdgit clone --depth 1 https://github.com/mamertofabian/mcp-everything-searchWrote 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/mamertofabian/mcp-everything-search/maid-plan-review)<a href="https://agentmods.dev/skills/mamertofabian/mcp-everything-search/maid-plan-review"><img src="https://agentmods.dev/badge/skills/mamertofabian/mcp-everything-search/maid-plan-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/mamertofabian/mcp-everything-search/maid-plan-review"><img src="https://agentmods.dev/badge/skills/mamertofabian/mcp-everything-search/maid-plan-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 | $0.00072 | $0.01634 |
| Opus 5.5 | $0.00029 | $0.00654 |
| Sonnet 5.5 | $0.00014 | $0.00327 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
maid-plan-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 11d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAID Plan Review
Review a manifest and its behavioral tests before implementation begins. This is the quality gate between planning and coding.
Distinguish draft inventory from an implementation-ready contract. Drafts under
manifests/drafts/ may exist before behavioral test files are created. Missing
planned tests, pytest "file not found", or E200 means the draft is not ready
to promote or implement yet; it is not automatically a defect in inventory
planning. Apply the behavioral-test and red-phase gates only when reviewing a
manifest for approval, promotion, or immediate implementation.
Rules
- NEVER modify the manifest or tests during review.
- NEVER proceed to implementation if blockers are found.
- ALWAYS confirm the red phase.
- Judge the plan, not the idea.
- Treat missing explicit signatures and missing field types as blockers.
- Treat
E200behavioral misses as blockers only for manifests presented as approval-ready, promotion-ready, or implementation-ready. - Treat missing rationale for important design choices as a revision item.
- Treat generic, missing, or unpaired
temptationsas blockers when the task has obvious implementation shortcuts.
Phase 1 — Locate the Manifest
Use the path provided by the user. If none is provided, inspect recent manifests/*.manifest.yaml files and pick the most likely draft. Ask only if the choice is ambiguous.
Phase 2 — Structural Review
Check:
- schema version
- specific goal
- manifest type
- created date
- adequate description
- valid
files.create,files.edit,files.read, andvalidatesections - lean task-specific
temptationswhen implementation gaming is plausible - sensible paths and dependency coverage
Phase 3 — Scope Review
Flag manifests that are too broad, too narrow, or missing critical read dependencies.
For current MAID manifests, distinguish contracted, scope-only, and contextual files:
files.createandfiles.editare the public artifact contract.files.scopeis writable implementation scope for files that need narrow no-artifact changes, such as route/page wiring covered by behavioral tests.files.readis dependency context and must not be used to authorize production edits. Test files may appear infiles.readas behavioral contract inputs, but production call-site rewiring belongs infiles.scopeorfiles.edit.- Require an intentional production edit to move from
files.readtofiles.scopewhen the file has no stable public artifact contract, or tofiles.editwhen the task changes/contracts public artifacts. - Be wary of forcing large existing public classes into
files.edit; MAID may then require declarations for the class's full public surface, expanding the manifest beyond the behavioral contract. Usefiles.scopefor narrow no-artifact wiring instead.
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.
- 11d ago First seen · 191 lines · 72 tokens per session scan A f2887f355cd4
maid-plan-review is a skill published in the GitHub repository mamertofabian/mcp-everything-search (367 stars, last pushed 12d ago), licensed MIT. It adds 72 tokens to every session and 1,634 once invoked, about $0.0003 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 2026-10-18.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.