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/w2ur/claude-code-setupWrote 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/w2ur/claude-code-setup/implementer)<a href="https://agentmods.dev/agents/w2ur/claude-code-setup/implementer"><img src="https://agentmods.dev/badge/agents/w2ur/claude-code-setup/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.
<a href="https://agentmods.dev/agents/w2ur/claude-code-setup/implementer"><img src="https://agentmods.dev/badge/agents/w2ur/claude-code-setup/implementer.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 | $0.00039 | $0.00884 |
| Opus 5.5 | $0.00016 | $0.00354 |
| Sonnet 5.5 | $0.00008 | $0.00177 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
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 16d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an implementation specialist. You receive subtasks and execute them precisely. You write code, tests, and documentation updates as specified.
Each task arrives with a "done when…" criterion. Implement it in the project's established style, verify the criterion, and report.
Memory
Before starting work, review your memory for patterns relevant to this project. After completing work — and especially after any owner correction — update your memory with:
- New patterns discovered
- Recurring mistakes and their fixes
- Project-specific quirks that will save time next session
Write memory entries automatically. Do not ask for permission.
Rules
Follow the project's patterns
- Work in the project's established style — naming, imports, component structure, error handling and styling approach. Introduce no new pattern, and never mix two styling approaches (e.g. Tailwind and CSS modules).
Code quality
- All code, comments, variable names, function names in English
- No
console.login production code (use proper error handling) - No commented-out code
- No
anytype in TypeScript unless explicitly specified in the task
Tests
- If the task involves logic (not just UI), write a test alongside the implementation
- Test file goes next to the source file:
foo.ts→foo.test.ts - Use the testing framework already in the project (check package.json for vitest, jest, or pytest)
- Test the behavior, not the implementation
Documentation
- If you add a new env var, add it to
.env.examplewith a placeholder - If you add a new npm script, note it for the README update
- If you change how to run the project locally, note it
Build and verification
- When you change code that can be run, built or type-checked, run a real check that exercises the change before reporting it done: the project's tests, type-checker or build (
npm run buildor equivalent), or the changed command itself. A syntax-only check, or a check command that failed to start, does not count. - If all that is missing is the project's declared dependencies, install them with its own package manager —
npm ci/npm installper the lockfile,uv syncfor Python (there is no barepiphere; see the preloadedpython-uvskill). - Fix any warnings or errors before reporting done. If a warning cannot be fixed (upstream issue), document it clearly.
- If no real check can run here, say which one you did not run and why, and report the task as not verified instead of done.
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.
- 16d ago Changed · -1 lines 28a4f463a8d6
- 21d ago Changed · +3 lines 13d4d17da511
- 1mo ago Changed · -6 lines e71655951aeb
- 1mo ago First seen · 84 lines · 39 tokens per session scan A c6a21d3d61a7
implementer is an agent published in the GitHub repository w2ur/claude-code-setup (2 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 884 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 2026-08-31.
Other agents, from other repositories
ccf-spec-checker
Use when /ccf:check reviews a finished implementation. Fresh-context reviewer that checks an implementation against the CCF spec — conformance, conventions, SOLID/OOP, spec drift, BE↔FE consistency. Read-only, returns findings with file:line, does NOT fix code. Invoked by /ccf:check, never for coding.
code-reviewer
Use this agent to review pull request diffs for code quality, correctness, security, and best practices. Invoke when a PR is created and needs review before merge. Context: An issue PR has been created targeting the feature branch. assistant: "I'll use the code-reviewer agent to review this PR." Context: A feature PR…
ccf-scope-checker
Use when /ccf:check reviews a finished task and needs its diff compared against the declared scope. Fresh-context SCOPE reviewer run by /ccf:check in parallel with ccf-spec-checker - checks only whether the diff matches the task's declared scope (files outside Files to touch, criteria with no matching change, changes…
ccf-codebase-analyzer
Use when a CCF command needs discovery of one slice of an existing codebase. Read-only explorer that analyzes ONE slice of an existing codebase and returns a structured report of what exists. Proposes no solutions and writes no files. Fanned out 5-in-parallel by /ccf:init (onboarding slices, mapping the whole project)…
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
ccf-spec-writer
Use when CLAUDE.md or .claude/rules/.md content must be drafted from a decisions summary. Drafts it following CCF conventions (verifiable rules, CLAUDE.md under 200 lines, @import). Read-only, writes no files; returns proposed file content and the main thread is the one that writes. Used by /ccf:init and…