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/commands/drobins25/craft/craft-story-continue)<a href="https://agentmods.dev/commands/drobins25/craft/craft-story-continue"><img src="https://agentmods.dev/badge/commands/drobins25/craft/craft-story-continue.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 | $0.00014 | $0.01268 |
| Opus 5 | $0.00007 | $0.00634 |
| Sonnet 5 | $0.00003 | $0.00254 |
| Haiku 4.5 | $0.00001 | $0.00127 |
Grade A, and why
story-continue 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 8d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Continue
Resume a story that was paused or interrupted.
Flow
Step 1: Find Current Story
Check state files:
Set PROJECT to ${CRAFT_PROJECT_ROOT:-.}.
Use Read to read $PROJECT/.craft/.global-state. Parse key=value pairs to extract CURRENT_STORY, ACTIVE_CYCLE.
Use Read to read $PROJECT/.craft/cycles/$ACTIVE_CYCLE/.state. Parse key=value pairs to extract CURRENT_CHUNK, TOTAL_CHUNKS, LAST_CHECKPOINT.
If no current story:
"No story in progress.
Pick one to work on?"
Use AskUserQuestion (options based on ready stories):
question: "No story in progress. Pick one to work on?"
header: "Story"
options:
- label: "[Story 1 name]"
description: "[N] chunks, [status]"
- label: "[Story 2 name]"
description: "[N] chunks, [status]"
- label: "[Story 3 name]"
description: "[N] chunks, [status]"
If user provides custom text: Ask a clarifying AskUserQuestion to confirm which story.
If story found:
Proceed to resume
Step 2: Show Context
"Resuming [Story Name]
Progress:
- Chunk 1: ✓ Complete
- Chunk 2: ✓ Complete
- Chunk 3: ◐ In progress ← you are here
- Chunk 4: ○ Pending
Last activity: [timestamp] Last checkpoint: [snapshot timestamp]
Continue with Chunk 3?"
Step 3: Verify State
Check if files match expected state:
# Compare current files with checkpoint
git diff [checkpoint-hash]
If clean:
Continue normally
If changes detected:
"Files have changed since last checkpoint:
auth.ts— modifiedlogin.tsx— modifiedHow to proceed?"
Use AskUserQuestion:
question: "Files changed since checkpoint. How to proceed?"
header: "Changes"
options:
- label: "Keep changes, continue"
description: "These are part of my progress"
- label: "Rollback to checkpoint"
description: "Discard changes, start fresh"
- label: "Review changes first"
description: "Show me the diff before deciding"
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.
- 8d ago First seen · 199 lines · 14 tokens per session scan A c47e5cf8bcf0
story-continue is a command published in the GitHub repository drobins25/craft (53 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 1,268 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
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.
unity-interview
Socratic interview flow — explores requirements, identifies edge cases, clarifies scope, and outputs a structured feature brief before any coding begins.
unity-workflow
Full development pipeline — clarify requirements, plan implementation, execute with agents, verify with review + tests.
unity-doctor
Diagnostic health check — verifies MCP connectivity, .claude/ integrity, Unity project structure, and hook registration.
unity-instincts
Manage the project's instinct library — view, promote, evolve, export, or import atomic learned behaviors captured automatically by PostToolUse observations.
unity-skill-stocktake
Audit all skills and agents in .claude/ for duplicates, stale references, never-loaded entries, broken globs, and frontmatter issues. Produces a cleanup report without modifying anything.