Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add drobins25/craft/plugin install 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/commands/drobins25/craft/craft-story-implement)<a href="https://agentmods.dev/commands/drobins25/craft/craft-story-implement"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-story-implement.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.12741 |
| Opus 5 | $0.00011 | $0.06370 |
| Sonnet 5 | $0.00004 | $0.02548 |
| Haiku 4.5 | $0.00002 | $0.01274 |
Grade A, and why
story-implement 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 7d 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 — 1,150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Implement
⛔ CRITICAL: YOU ARE THE ORCHESTRATOR, NOT THE IMPLEMENTER
You must NOT write implementation code directly. For EVERY chunk, you MUST use the Task tool to invoke the implementer agent:
Task tool:
subagent_type: "craft:implementer"
description: "Implement chunk N of [story]"
prompt: [chunk details, story context, TDD requirement]
If you find yourself about to write code → STOP → use Task tool instead.
⛔ CRITICAL: VALIDATION CHAIN IS INLINE
Do NOT invoke the validate-chunk skill (craft:validate-chunk) during the implementation loop. The validate-chunk skill exists for manual user invocation only. story-implement owns the validation chain directly:
- Invoke chunk-validator agent via Task tool
- Route PASSED/PARTIAL inline
- Route FAILED via Read
${CLAUDE_PLUGIN_ROOT}/commands/references/validate-fix-loop.md
⛔ CRITICAL: ALL VALIDATION RUNS SYNCHRONOUSLY
NEVER use run_in_background: true for test, typecheck, lint, or build commands. All validation must complete synchronously — results confirmed before marking any chunk or story done. This applies to:
- Per-chunk validation (Step 4)
- Quality gates (Step 5)
- Any "verify nothing broke" test runs
Background test runs cause orphaned failure notifications that appear after stories are already marked complete. If a command is slow, wait for it.
Implement a story that's already been designed. This is pure Implement Phase — chunks exist, decisions are locked, just execute.
Project Root
All .craft/ paths in this command are relative to $CRAFT_PROJECT_ROOT (set at session start). Use ${CRAFT_PROJECT_ROOT:-.} as prefix when constructing paths. Pass the project root to all subagents.
Prerequisites & Status Guards
Before implementation, validate story location and status:
Location check:
- If story is in
.craft/backlog/→ BLOCK:
Use AskUserQuestion:
question: "This story is in the backlog. Assign it to a cycle first?"
header: "Assign"
options:
- label: "Assign to [active cycle] (Recommended)"
description: "Add to current cycle and implement"
- label: "Create new cycle for it"
description: "Start a new cycle with this story"
- label: "Cancel"
description: "Go back"
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.
- 7d ago First seen · 1,150 lines · 22 tokens per session scan A 6da03dd462b3
story-implement is a command published in the GitHub repository drobins25/craft (53 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 12,741 once invoked, about $0.0001 per session on Opus 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 commands, from other repositories
feedback
Collect feedback and create GitHub issue (bug report, feature request).
todo
Backlog queue for Kanban Mode — add, list, or pick the next card.
claudehut-learning-report
Show the ClaudeHut learning scoreboard — measured memory health (store size, reinforcement, effectiveness/recurrence, quality) so you can tell whether the agent is actually getting smarter across sessions. One-shot, read-only.
oss-docs
(user-owned) oss-docs harness — README 4-locale + docs-site publishing for the moai-adk-go OSS project (adk.mo.ai.kr, Vercel auto-deploy).
portfolio
Show a read-only hub-wide portfolio of canonical Ideas and active Projects without duplicating topic-owned records.
clean
Identify and safely remove dead code with test verification.