fire-loop

A command that repeatedly works on a task until it is complete, while checking for stalled, repeating, worsening, or blocked progress.

In plain words
What is it for?
Use it for tasks with clear completion conditions, such as fixing a bug and running tests, with limits on iterations and built-in progress handling.
Why use it?
It helps long-running tasks recover from unproductive attempts and stop when continuing is unlikely to help.

Command

Install

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.

agentmods
npx agentmods add commands/thierryn/fire-flow/fire-loop
Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,784 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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.

ModelPer sessionOnce 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

Measured 2d ago against content hash d44a11090f6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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
commands/fire-loop.md · 1,156 lines

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)"

Read the full file on GitHub · 1,156 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.

  1. 2d ago First seen · 1,156 lines · 21 tokens per session scan B d44a11090f6c

Subscribe to this mod's changes

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.