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/forsonny/The-Crucible-Writing-System-For-ClaudeWrote 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/forsonny/the-crucible-writing-system-for-claude/crucible-continue)<a href="https://agentmods.dev/commands/forsonny/the-crucible-writing-system-for-claude/crucible-continue"><img src="https://agentmods.dev/badge/commands/forsonny/the-crucible-writing-system-for-claude/crucible-continue/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/commands/forsonny/the-crucible-writing-system-for-claude/crucible-continue"><img src="https://agentmods.dev/badge/commands/forsonny/the-crucible-writing-system-for-claude/crucible-continue.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 | $0.00017 | $0.01200 |
| Opus 5 | $0.00009 | $0.00600 |
| Sonnet 5 | $0.00003 | $0.00240 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
crucible-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 12d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/crucible-continue
Resume your Crucible project from wherever you left off.
CRITICAL: How to Present Options
When presenting choices to the user, you MUST use the AskUserQuestion tool.
WRONG - Never do this:
Would you like to:
A) Continue planning
B) Review premise
C) Start fresh
D) Something else
RIGHT - Always do this:
Use the AskUserQuestion tool with this format:
{
"questions": [
{
"header": "Continue",
"question": "How would you like to proceed?",
"options": [
{"label": "Continue planning", "description": "Resume from current position"},
{"label": "Review premise", "description": "Check the premise before continuing"},
{"label": "Start fresh", "description": "Begin planning with a new premise"},
{"label": "Something else", "description": "Do something different"}
],
"multiSelect": false
}
]
}
Execution Steps
- Read state files to determine current phase
- Display project status as plain text (title, phase, progress)
- Use AskUserQuestion tool to present options (NOT plain text A/B/C/D)
- Invoke the appropriate skill based on user selection
State Files to Check
.crucible/state/planning-state.json- Planning progress.crucible/state/outline-state.json- Outlining progress.crucible/state/draft-state.json- Writing progress.crucible/state/edit-state.json- Editing progress
CRITICAL: Planning Completion Check
Planning has TWO phases that must BOTH be complete:
- Phase 2 (Q&A): All 9 documents marked complete in
progress.documents_complete - Phase 3 (Compilation): Actual planning files generated by
compile_documents.py
To verify planning is truly complete, check for actual files:
# Check if planning documents were generated
ls <project_path>/planning/crucible-thesis.md
If Q&A is done (9/9 docs) but crucible-thesis.md does NOT exist:
- Planning is NOT complete - Phase 3 was never run
- Report: "Q&A complete but planning documents not generated"
- Offer to run compilation:
python <plugin_path>/skills/crucible-planner/scripts/compile_documents.py "<project_path>"
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.
- 12d ago First seen · 171 lines · 17 tokens per session scan A d8d1a193fc6e
crucible-continue is a command published in the GitHub repository forsonny/The-Crucible-Writing-System-For-Claude (60 stars, last pushed 8mo ago), licensed MIT. It adds 17 tokens to every session and 1,200 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.