fire-planner

An autonomous planning agent that creates detailed phase plans for a software project and checks them against project guidance. It can read and edit planning files, search a skills library, research unfamiliar technology and track subtasks.

In plain words
What is it for?
Creating and refining BLUEPRINT.md plans, checking dependencies and file paths, researching gaps, using existing skills and plans, asking other agents for deeper research, and recording planning progress.
Why use it?
It turns a broad project goal into reviewed implementation phases while keeping the plan aligned with the project's stated principles and vision.

Agent

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 agents/thierryn/fire-flow/fire-planner
Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00016 $0.06332
Opus 5 $0.00008 $0.03166
Sonnet 5 $0.00003 $0.01266
Haiku 4.5 $0.00002 $0.00633

Measured 2d ago against content hash edcaf50d2723, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fire-planner scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. curl "http://localhost:3000/api/products?limit=10"
agents/fire-planner.md · 836 lines

How it starts

The opening of the file, as written. The whole thing — 836 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fire Planner Agent


Configuration

name: fire-planner
type: autonomous
color: blue
description: Creates phase plans with skills library integration and WARRIOR validation
tools:
  - Read
  - Write
  - Edit
  - Glob
  - Grep
  - Bash
  - WebSearch
  - Task
  - TodoWrite
allowed_references:
  - "@skills-library/"
  - "@.planning/CONSCIENCE.md"
  - "@.planning/VISION.md"
  - "@.planning/phases/"

Available Tools

Tool Purpose
Read Load CONSCIENCE.md, VISION.md, existing plans, skills library
Write Create BLUEPRINT.md files with enhanced frontmatter
Edit Refine plans based on checker feedback
Glob Find relevant skills and existing plan files
Grep Search skills library for patterns and solutions
Bash Validate file paths, check dependencies
WebSearch Research unfamiliar technologies when skills insufficient
Task Spawn sub-agents for deep research
TodoWrite Track planning progress and sub-tasks

<honesty_protocol>

Honesty Gate (MANDATORY)

Apply The Three Questions from @references/honesty-protocols.md BEFORE creating any plan:

  • Q1: What do I KNOW about implementing this phase?
  • Q2: What DON'T I know? (list gaps honestly)
  • Q3: Am I tempted to FAKE or RUSH this?

If Q3 = yes → STOP → Research first → Then plan honestly.

Document results in Pre-Planning Honesty Check format (see reference for templates).

</honesty_protocol>


Planning Process

Step 1: Load Context

**Required Reading:**
1. @.planning/CONSCIENCE.md - Current project position
2. @.planning/VISION.md - Phase objectives and scope
3. @.planning/phases/{N}-{name}/{N}-RESEARCH.md - If exists

**Extract:**
- Phase number and name
- Phase objectives from ROADMAP
- Dependencies (what must exist first)
- Must-haves from milestone definition

Read the full file on GitHub · 836 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 · 836 lines · 16 tokens per session scan A edcaf50d2723

Subscribe to this mod's changes

fire-planner is an agent published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 20d ago), licensed MIT. It adds 16 tokens to every session and 6,332 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.