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/ThierryN/fire-flowWrote 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/thierryn/fire-flow/fire-6-resume)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-6-resume"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-6-resume.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 | $0.00010 | $0.04186 |
| Opus 5 | $0.00005 | $0.02093 |
| Sonnet 5 | $0.00002 | $0.00837 |
| Haiku 4.5 | $0.00001 | $0.00419 |
Grade C, and why
fire-6-resume scanned grade C 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 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
> — malicious skill instructions injected to collect API keys at 2 AM. How it starts
The opening of the file, as written. The whole thing — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-6-resume
Resume work from most recent handoff with full context restoration
Purpose
Resume a project from a previous session by loading the most recent WARRIOR handoff file, displaying a comprehensive status summary, checking for incomplete work, and routing to the appropriate next action. This command ensures zero context loss between sessions.
Arguments
arguments: none
optional_flags:
--handoff: "Specify handoff file to load (e.g., --handoff project_2026-01-20.md)"
--list: "List available handoffs without loading"
--diff: "Show changes since last handoff"
Process
Step 1: Find Most Recent Handoff
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
DOMINION FLOW > SESSION RESUME
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Scan Handoff Directory:
ls -t ~/.claude/warrior-handoffs/*.md | head -5
If --list flag:
┌─────────────────────────────────────────────────────────────────────────────┐
│ AVAILABLE HANDOFFS │
├─────────────────────────────────────────────────────────────────────────────┤
│ │
│ Recent handoffs (newest first): │
│ │
│ 1. my-project_2026-01-22.md (2 hours ago) │
│ Phase 3 - Pattern Computation | Status: Executing │
│ │
│ 2. my-project_2026-01-21.md (1 day ago) │
│ Phase 2 - Typology | Status: Complete │
│ │
│ 3. book-writer-app_2026-01-20.md (2 days ago) │
│ Phase 4 - Export | Status: Verifying │
│ │
│ Load specific handoff: /fire-6-resume --handoff {filename} │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
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 · 508 lines · 10 tokens per session scan C 94873b760bc6
fire-6-resume is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 25d ago), licensed MIT. It adds 10 tokens to every session and 4,186 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
review
Review the current diff against project memory.
help
Quick reference for all Attune commands.
tdd
Test-driven change — write the failing test first, then implement.
lfe-plan-critique
Run a 5-lens pre-build critique of the approved active plan before the Builder starts. Acts as the Architect persona, read-only on src/. Writes .plans/plancritique.md. Use immediately after Brain approves activeplan.md.
rc-plano
Fluxo Explore→Plan — investiga antes de codar e entrega um plano para aprovação.
lfe-improve-architecture
Find deepening opportunities in the codebase — turn shallow modules into deep ones. Use in Phase 5 (Hygiene sub-pipeline) or when scheduled by session count.