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-loopgit 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 | $0.00021 | $0.08784 |
| Opus 5 | $0.00010 | $0.04392 |
| Sonnet 5 | $0.00004 | $0.01757 |
| Haiku 4.5 | $0.00002 | $0.00878 |
Grade B, and why
fire-loop scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
If Qdrant is unreachable (connection refused on port 6335), log WARNING and fall back to file-based memory search: grep across `~/.claude/warrior-handoffs/` and `~/.claude/reflections/` for keyword matches. This is slowe How it starts
The opening of the file, as written. The whole thing — 1,156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-loop
Self-iterating autonomous loop with quantitative convergence detection, approach rotation, and context-aware execution
Purpose
Start a self-iterating loop that persists until task completion. Integrates Dominion Flow's full v3 intelligence stack:
- Circuit Breaker — Hard numerical thresholds that detect stalling, spinning, and degradation
- Error Classification — PROGRESS/STALLED/SPINNING/DEGRADED/BLOCKED state machine driving different responses
- Context Engineering — Recitation pattern keeps plan in attention window; .powerignore excludes noise
- Decision-Time Guidance — Skills library micro-instructions injected at error/decision points
- Sabbath Rest — Context rot detection with state persistence for clean resume
Key difference from /fire-loop: Power Loop is self-aware. It measures its own health, rotates approaches when stuck, and stops before wasting iterations on unsolvable problems.
Arguments
arguments:
prompt:
required: true
type: string
description: "Task description with clear completion criteria"
example: '/fire-loop "Fix login bug. Tests must pass. Output DONE when fixed."'
options:
--max-iterations:
type: number
default: 50
description: "Safety limit — stop after N iterations"
--completion-promise:
type: string
default: "DONE"
description: "Exact text that signals successful completion"
--checkpoint-interval:
type: number
default: 5
description: "Save checkpoint every N iterations"
--apply-skills:
type: boolean
default: true
description: "Search and apply relevant skills from library"
--discover:
type: boolean
default: false
description: "Run /fire-discover at start to find relevant patterns"
--no-circuit-breaker:
type: boolean
default: false
description: "Disable circuit breaker (not recommended)"
--aggressive:
type: boolean
default: false
description: "Tighter thresholds: stall=2, spin=3, decline=40%"
--autonomous:
type: boolean
default: false
description: "Auto-route review gate verdicts without human checkpoints (used by /fire-autonomous)"
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 · 1,156 lines · 21 tokens per session scan B d44a11090f6c
fire-loop is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 20d ago), licensed MIT. It adds 21 tokens to every session and 8,784 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.