What is maid-implementer?

A coding workflow skill that implements an approved MAID manifest, a file describing the agreed code changes and tests. It limits edits to declared files and runs validation while implementing.

Use it to build a feature or change from an approved manifest, run its checks, and iterate until validation passes.

It reduces accidental changes outside the plan and catches failures before the work is handed off. It also separates approved implementation from planning.

How mamertofabian/mcp-everything-search configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/mamertofabian/mcp-everything-search/main/.claude/skills/maid-implementer/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/mamertofabian/mcp-everything-search

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mamertofabian/mcp-everything-search/maid-implementer/github.svg)](https://agentmods.dev/skills/mamertofabian/mcp-everything-search/maid-implementer)

Your own site

<a href="https://agentmods.dev/skills/mamertofabian/mcp-everything-search/maid-implementer"><img src="https://agentmods.dev/badge/skills/mamertofabian/mcp-everything-search/maid-implementer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mamertofabian/mcp-everything-search/maid-implementer"><img src="https://agentmods.dev/badge/skills/mamertofabian/mcp-everything-search/maid-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,682 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00058	$0.02682
Opus 5.5	$0.00023	$0.01073
Sonnet 5.5	$0.00012	$0.00536
Haiku 4.5	$0.00006	$0.00268

Measured 11d ago against content hash f038d89f81a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

maid-implementer 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.

.claude/skills/maid-implementer/SKILL.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MAID Implementer

Execute code implementation against an approved MAID manifest. The manifest is the contract.

When the starting point is still manifests/drafts/*.manifest.yaml, use maid-implement-draft to harden, lock, and promote first. This skill implements an already-approved (typically promoted) contract.

Rules

Load the manifest first.
Implement only what the manifest declares.
files.create and files.edit declare contracted public artifacts.
files.scope declares writable implementation files that have no stable public artifact contract, such as route/page wiring covered by behavioral tests.
files.read is dependency context, not writable production scope. Do not edit production files listed only in files.read; stop for plan revision and move intentional no-artifact wiring to files.scope.
Implementer sessions run validation gates with --packet; for example, maid validate --packet and maid verify --profile agent-retry --since <baseline>.
strict gates are the default. Use --legacy-gates only as a bounded migration aid when comparing behavior against pre-flip defaults.
Run maid validate --mode implementation after implementation.
Run all manifest validate commands.
NEVER modify files not listed in the manifest files.create, files.edit, files.scope, or files.delete.
NEVER modify the manifest during implementation.
NEVER modify behavioral tests unless the user explicitly approves changing the contract.
If implementation validation exposes a bad manifest, write plan-revision.md explaining the issue and stop. Do not force tests green by working around a bad plan.
If the manifest has temptations, restate the relevant risk/procedure pairs before editing and treat each instead as the working procedure.

Packet-Driven Retry Gates

When a packet-aware gate fails, read .maid/last-failure-packet.json instead of re-exploring the repository. The packet is the retry context: failed command argv, exit code, project root, failed manifest excerpts, diagnostics, next_action repair recipes, failed-command output tails, and environment versions.

Read the full file on GitHub · 305 lines

Changes

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 · 305 lines · 58 tokens per session scan A f038d89f81a3

Subscribe to this mod's changes

maid-implementer is a skill published in the GitHub repository mamertofabian/mcp-everything-search (367 stars, last pushed 12d ago), licensed MIT. It adds 58 tokens to every session and 2,682 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.

Planning Testing

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.

davila7/claude-code-templates · 43 tokens

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".

apache/tika · 50 tokens

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.

davidondrej/skills · 68 tokens

mcp-everything-search: Skill for Claude Code