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.
npx agentmods add commands/thierryn/fire-flow/fire-loop-stopgit clone --depth 1 https://github.com/ThierryN/fire-flowWhat 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 | $0.00008 | $0.01104 |
| Opus 5 | $0.00004 | $0.00552 |
| Sonnet 5 | $0.00002 | $0.00221 |
| Haiku 4.5 | $0.00001 | $0.00110 |
Grade A, and why
fire-loop-stop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-loop-stop
Cancel active Power Loop with progress preservation
Purpose
Safely cancel an active Power Loop, preserving all progress made and updating tracking files. Use this when you need to:
- Stop a loop that's not making progress
- Pause work to resume later
- Cancel a loop started with wrong parameters
Process
Step 1: Check for Active Loop
if [ ! -f ".planning/loops/active-loop.json" ]; then
echo "No active Power Loop found."
exit 0
fi
Step 2: Read Loop State
LOOP_ID=$(jq -r '.id' .planning/loops/active-loop.json)
LOOP_FILE=$(jq -r '.loop_file' .planning/loops/active-loop.json)
CURRENT_ITERATION=$(jq -r '.current_iteration' .planning/loops/active-loop.json)
MAX_ITERATIONS=$(jq -r '.max_iterations' .planning/loops/active-loop.json)
Step 3: Create Sabbath Rest Snapshot
Save current state for potential resume:
## .planning/loops/sabbath-${LOOP_ID}-stopped.md
---
loop_id: ${LOOP_ID}
iteration: [current]
timestamp: [ISO]
reason: user_requested_stop
---
## State at Stop
### Progress Summary
- Iterations completed: [N]
- Last action: [description]
### Files Modified
- [file]: [change summary]
### Next Steps (if resumed)
1. [what to do next]
### Key Context
[Critical information for resume]
Step 4: Update Loop File
Add cancellation entry to loop file:
## Final Result
- **Status:** cancelled_by_user
- **Total Iterations:** [current_iteration]
- **Cancelled At:** [timestamp]
- **Reason:** User requested stop via /fire-loop-stop
### Progress at Cancellation
[Summary of what was accomplished]
### Files Changed
- [list of files modified during loop]
### Resume Instructions
To resume this work:
/fire-loop-resume ${LOOP_ID}
Step 5: Clean Up Active Loop
# Archive the active loop config
mv .planning/loops/active-loop.json ".planning/loops/stopped-${LOOP_ID}.json"
Step 6: Update CONSCIENCE.md
Remove the "Active Power Loop" section from CONSCIENCE.md.
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.
- 2d ago First seen · 199 lines · 8 tokens per session scan A 02323a2bc7bc
fire-loop-stop is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 20d ago), licensed MIT. It adds 8 tokens to every session and 1,104 once invoked, about $0.0000 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.