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-evolver/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-evolver)<a href="https://agentmods.dev/skills/mamertofabian/mcp-everything-search/maid-evolver"><img src="https://agentmods.dev/badge/skills/mamertofabian/mcp-everything-search/maid-evolver/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-evolver"><img src="https://agentmods.dev/badge/skills/mamertofabian/mcp-everything-search/maid-evolver.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 | $0.00053 | $0.02786 |
| Opus 5.5 | $0.00021 | $0.01114 |
| Sonnet 5.5 | $0.00011 | $0.00557 |
| Haiku 4.5 | $0.00005 | $0.00279 |
Grade A, and why
maid-evolver 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAID Evolver Skill
Rules
- NEVER silently rewrite a locked manifest. For a contract in the current
unmerged task, revise the existing draft or promoted manifest in place; use
maid plan revisefor a locked plan so its lock and red evidence remain valid. - Treat a contract accepted into shared project history as durable, regardless of branch name (including integration and release branches). Intentional changes to a durable contract require a new manifest; do not create follow-on or superseding manifests just to revise unmerged work.
- ALWAYS choose the least disruptive evolution strategy (chain merge before supersede).
- ALWAYS validate that the evolution does not break dependent manifests.
- ALWAYS update behavioral tests to match the new contract.
The Core Question
First check repository policy and history to determine whether the affected
manifest belongs to the current unmerged task or is already accepted shared
history. A local task commit alone does not make the contract durable; a
contract accepted from an earlier task is not mutable just because it has not
reached the default branch. If acceptance is unclear, clarify it before rewriting.
For the current task's unaccepted contract, revise it in place. For a locked
plan, run maid plan revise <manifest> --reason "<text>"; choose the evidence-preserving or
stash-backed option appropriate to the change. Review the revised contract and
confirm the updated lock before implementation continues.
--stash-implementation hides uncommitted implementation changes only; it
cannot remove implementation already committed on a task branch. If revised
tests expose missing behavior in committed code, plain maid plan revise can
capture that failure before the fix. If they already pass and the revision
cannot preserve valid evidence, stop and report the evidence blocker with the
pre-implementation baseline needed for recovery. Do not reset shared history,
weaken tests, or bypass evidence requirements. See
docs/draft-manifest-workflow.md, "Revision Evidence After Implementation",
for the evidence decision path.
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 · 361 lines · 53 tokens per session scan A e977d6fa7db4
maid-evolver is a skill published in the GitHub repository mamertofabian/mcp-everything-search (367 stars, last pushed 12d ago), licensed MIT. It adds 53 tokens to every session and 2,786 once invoked, about $0.0002 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…