What is story-implement-auto?

An unattended story-implementation command that works through every ready story in the active cycle, a planned work period.

Use it when fully designed stories should be implemented automatically in filename order until none remain or a failure stops the process.

It removes the need for interactive choices while implementing a sequence of prepared stories.

story-implement-auto — Command for Claude Code by drobins25

Install

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.

Claude Code

/plugin marketplace add drobins25/craft

Claude Code

/plugin install craft

Made for: Claude Code.

Or install craft, the plugin that ships this one along with the rest of its 11 skills, 33 commands, 27 agents, 7 hooks, 1 MCP server.

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/commands/drobins25/craft/craft-story-implement-auto/github.svg)](https://agentmods.dev/commands/drobins25/craft/craft-story-implement-auto)

Your own site

<a href="https://agentmods.dev/commands/drobins25/craft/craft-story-implement-auto"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-story-implement-auto/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/commands/drobins25/craft/craft-story-implement-auto"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-story-implement-auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,447 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	$0.00023	$0.01447
Opus 5	$0.00012	$0.00724
Sonnet 5	$0.00005	$0.00289
Haiku 4.5	$0.00002	$0.00145

Measured 9d ago against content hash bcd918835504, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

story-implement-auto 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 9d 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.

commands/craft-story-implement-auto.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Story Implement Auto

Run craft:story-implement autonomously. The user is not present and wants all ready stories in the active cycle completed.

How This Works

This command sets autonomous behavioral overrides, then delegates to the full implementation flow via skill invocation.

After startup and story selection, invoke the implementation skill:

Skill tool:
  skill: "craft:craft-story-implement"
  args: "[story-file-path]"

The skill contains the full implementation loop — agent invocation, validation, learnings, everything. This command only specifies what's different when no user is present. Apply the overrides below to every decision point in the skill's flow.

Autonomous Behavior

No AskUserQuestion calls. At every decision point in craft:story-implement, choose the recommended option automatically. Never wait for user input.
Auto-pick stories. Select the next status: ready story in the active cycle, in filename order. No story selection prompt.
Chain stories. After completing a story, pick the next ready one. Continue until no more ready stories or failure.
Auto-answer defaults. Package manager: auto-detect from lockfiles, default to npm. Test infra: set up Vitest if missing. Spark verification: self-check acceptance criteria — only stop on provably unmet (file doesn't exist, test doesn't pass), not subjective judgments.
Validation via skill. Same craft:validate-chunk skill invocation as craft:story-implement. The skill handles all routing autonomously — no AskUserQuestion calls needed since refine-chunk and test-fix are already non-interactive.

Startup Sanity Check

First, mark autonomous mode so compaction recovery knows how to resume:

${CLAUDE_PLUGIN_ROOT}/hooks/scripts/update-global-state.sh RUN_MODE "autonomous"

Then read .global-state and handle stale state from a crashed previous run:

Condition	Action
No `ACTIVE_CYCLE`	"No active cycle." EXIT.
`CURRENT_STORY` set, story is `complete`	Stale state — clear CURRENT_STORY, CRAFT_WRITE_ENABLED, cycle state. Proceed to story selection.
`CURRENT_STORY` set, story is `active`, all chunks done	Crashed before `complete-story.sh`. Skip to story completion flow. NOTE: the dead session's `.craft/.commit-manifest` is gone (session-start clears it), so if you resume past the manifest-write sub-step (story-implement 7b) without re-writing it, `complete-story.sh` makes NO commit by design ("no manifest found"). Re-run sub-step 7b before Mark Complete, or surface "completion commit skipped (no manifest)" in the final report.
`CURRENT_STORY` set, story is `active`, chunks incomplete	Resume from current chunk. Trust story frontmatter (`chunks_complete + 1`) as ground truth.
`CRAFT_WRITE_ENABLED` set but no `CURRENT_STORY`	Orphaned flag — clear it. Proceed to story selection.
Clean state	Normal start. Proceed to story selection.

Read the full file on GitHub · 99 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.

9d ago First seen · 99 lines · 23 tokens per session scan A bcd918835504

Subscribe to this mod's changes

story-implement-auto is a command published in the GitHub repository drobins25/craft (60 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 1,447 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.

Project management agentic-ai agentic-workflow ai-coding-assistant anthropic anthropic-claude claude

story-implement-auto

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Story Implement Auto

How This Works

Autonomous Behavior

Startup Sanity Check

What this file has done since we first saw it

Other commands, from other repositories

claudehut-learning-report

amend-plan

sdd

traceability-gen

project

ccc-makeover