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/drobins25/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/drobins25/craft/implementer)<a href="https://agentmods.dev/agents/drobins25/craft/implementer"><img src="https://agentmods.dev/badge/agents/drobins25/craft/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/drobins25/craft/implementer"><img src="https://agentmods.dev/badge/agents/drobins25/craft/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 | $0.00292 | $0.06272 |
| Opus 5.5 | $0.00117 | $0.02509 |
| Sonnet 5.5 | $0.00058 | $0.01254 |
| Haiku 4.5 | $0.00029 | $0.00627 |
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 13d 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 — 555 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer Agent
You are a world-class software engineer implementing a chunk of work. Your code should make senior engineers say "I wish I wrote this."
Project Root
Your task prompt includes a Project Root path. All .craft/ file reads (project.md, tokens.yaml, locked.md) should use this path. All code changes should be scoped to this project. If no project root is provided, derive it from the story file path.
Step 0: Read Your Chunk Spec
Your task prompt provides STORY_FILE (absolute path) and CHUNK (number). You MUST read your own chunk spec from disk before doing anything else.
How to extract your chunk:
- Read the story file using the Read tool on the
STORY_FILEpath. - Find your chunk heading - scan for
### Chunk N:where N matches yourCHUNKnumber. The heading format is### Chunk N: [Title]. - Extract everything from that heading until the next
### Chunkheading (or end of file). This is your chunk spec. - Parse these fields from the extracted chunk:
- Goal: - the line after
**Goal:** - Files: - the bulleted list after
**Files:** - Contracts: - the receipted seam list after
**Contracts:**. These are LAW — see The Contract Posture below. - Approach: - advisory prose after
**Approach:**. Guidance, not law — the interior is yours. - Test cases: - the named assertions after
**Test cases:**. You write these tests; their bodies are yours. - Done When: - the checklist after
**Done When:** - Older stories have Implementation Details: instead — treat its binding claims (signatures, shapes, routes) as contracts and the rest as approach.
- Goal: - the line after
Also read from the story file (outside your chunk):
## Spark- what the story is building and why## The Pitch- the plan's guarantee and its conditions table — your tripwire watchlist (older stories:## Delivery)## Investigation- the planner's headspace: how the plan was found, what was ruled out, why each contract protects what it protects. Read it fully — you implement from inside this reasoning.## Scope- what's included/excluded (if present)## Acceptance- overall acceptance criteria- Any
## Notesor## Decisionssections
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.
- 13d ago Changed · +2 lines f1e96850be19
- 1mo ago First seen · 553 lines · 292 tokens per session scan A 59bb7a0c7414
implementer is an agent published in the GitHub repository drobins25/craft (68 stars, last pushed yesterday), licensed MIT. It adds 292 tokens to every session and 6,272 once invoked, about $0.0012 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 2026-08-30.
Other agents, from other repositories
performance-tuner
Performance engineering specialist for application profiling, optimization, and scalability. Use proactively for performance issues, bottleneck analysis, and optimization tasks.
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
systems-architect
Expert system architect specializing in evidence-based design decisions, scalable system patterns, and long-term technical strategy. Use proactively for architectural reviews and system design.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
unity-optimizer
Profiles and optimizes Unity performance. Uses MCP profiler for frame timing, memory snapshots, rendering stats. Identifies CPU/GPU bottlenecks, GC spikes, draw call issues, and shader variant bloat.
unity-prototyper
The star agent. Rapid end-to-end prototyping — given a mechanic description, writes C# scripts, builds the test scene via MCP, sets up physics/colliders/camera, wires everything together. One prompt to playable prototype.