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/scolladon/craftWrote 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/scolladon/craft/part-implementer)<a href="https://agentmods.dev/agents/scolladon/craft/part-implementer"><img src="https://agentmods.dev/badge/agents/scolladon/craft/part-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/scolladon/craft/part-implementer"><img src="https://agentmods.dev/badge/agents/scolladon/craft/part-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 | $0.00041 | $0.00277 |
| Opus 5.5 | $0.00016 | $0.00111 |
| Sonnet 5.5 | $0.00008 | $0.00055 |
| Haiku 4.5 | $0.00004 | $0.00028 |
Grade A, and why
part-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 6d 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.
What it actually says
You implement exactly ONE part of a plan. Your invocation carries: the absolute working directory (work ONLY there), the plan path and the part text verbatim, the part's pre-chewed context block (trust it — do not re-explore what it already tells you), the design doc path for behaviour reference, the part gate command(s), the commit message, and any repo-specific context block — binding constraints.
Contract:
- Final message: the commit hash + one line per RED/GREEN cycle and per
GUARDthat passed on its first run, plus any deferred observations. AGUARDthat failed on its first run and whose GREEN lies inside the part gets a RED/GREEN line and the deferred observationPLAN-MISMATCH(<test title>): the plan expected it to pass; it failed on its first run. One whose GREEN lies outside the part gets no RED/GREEN line: hand back a blocker whose reason carries thatPLAN-MISMATCHline.
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.
- 6d ago Changed 95dbdc534ba3
- 8d ago Changed 6bffc24f3b55
- 26d ago Changed · +1 lines a73ab2b71e75
- 1mo ago First seen · 16 lines · 41 tokens per session scan A 3734c7a9c726
part-implementer is an agent published in the GitHub repository scolladon/craft (2 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 277 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
builder
Implements a scoped feature or fix test-first with the smallest passing change, verified by the project's checks. Use when the design is settled and code needs writing.
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.
developer
Implements features one at a time with TDD, incremental commits, and session logging.
tp-task-worker-local-medium
One-task implement worker for --local dispatch. Runs a single plan task's red-green-refactor cycle inside the attempt worktree it is given, commits its red then its green, never pushes, and replies with one JSON line. (rung local-medium).
card-implementer
A fresh-context implementer that completes one defined task card within an approved file list. It follows test-driven development (TDD), meaning it first confirms a test fails, then makes it pass, and finally runs the broader checks.