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-1a-new)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-1a-new"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-1a-new.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 | $0.00012 | $0.02097 |
| Opus 5 | $0.00006 | $0.01048 |
| Sonnet 5 | $0.00002 | $0.00419 |
| Haiku 4.5 | $0.00001 | $0.00210 |
Grade A, and why
fire-1a-new 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 7d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-1a-new
Initialize a new project — scaffold directory, gather requirements, create .planning/ structure
Purpose
Create the project foundation: directory, requirements gathering, and the complete .planning/ file structure. This is Step 1 of 3 in project initialization.
Flow: /fire-1a-new → /fire-1b-research → /fire-1c-setup
Arguments
arguments: none
optional_flags:
--name: "Project name (will prompt if not provided)"
--path: "Project path (defaults to current directory)"
--minimal: "Skip adaptive questioning, use defaults"
EXECUTION ORDER
STEP 1: Environment Validation → create NEW project directory
STEP 2: Gather Requirements → MODE GATE question, backward interview if needed
STEP 3: Create .planning/ → mkdir + touch ALL files (EXACT names, no renaming)
FINAL: Chain to next command → tell user to run /fire-1b-research
Complete each step before starting the next. No skipping.
Step 1: Environment Validation
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
DOMINION FLOW > PROJECT INITIALIZATION
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- Create a NEW project directory — Do NOT initialize inside an existing project. If the current directory has source code,
package.json, or.planning/, create a new directory:
Usemkdir -p {project-path}/{project-name} cd {project-path}/{project-name} git init--pathflag if provided, otherwise ask the user or derive from project name. - Check if
.planning/already exists (warn if so — means project was already initialized) - Verify write permissions
- Create git repo if not present
Step 2: Gather Requirements
Core Questions:
- What is this project? (one sentence)
- Who is the primary user?
- What is the core value it provides?
- What are the non-negotiable features (must-haves)?
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.
- 7d ago First seen · 252 lines · 12 tokens per session scan A 1bbee02dad00
fire-1a-new is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 25d ago), licensed MIT. It adds 12 tokens to every session and 2,097 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
epic-claim
Claim an epic issue, stamp coordination state, and sync local ownership.
epic-decompose
Break an epic into task children without creating task branches.
epic-review
Mark epic review requested, approved, or changes requested.
epic-sync
Sync epic issue bodies, labels, and local coordination snapshots from GitHub.
epic-unblock
Sweep blocked epic issues and reopen anything whose dependencies are closed.
epic-validate
Validate epic readiness, dependencies, and coordination policy.