fire-project-researcher

fire-project-researcher is an agent for Claude Code from ThierryN/fire-flow. It costs 20 tokens per session (1,000 once invoked), scanned B, original, MIT.

An autonomous research agent for investigating a project or milestone before planning begins. It examines a chosen area, such as the technology stack, features, risks, or user experience, and saves its findings to a planning file.

In plain words
What is it for?
Use it during new project or milestone setup to research dependencies, build tools, proposed features, user stories, or acceptance criteria.
Why use it?
It gathers background information before a roadmap is created, reducing the chance of planning from incomplete assumptions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the dominion-flow plugin — 5 skills, 51 commands, 13 agents shipped together

Good fit Use it during new project or milestone setup to research dependencies, build…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thierryn/fire-flow/fire-project-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow

Made for: Claude Code.

Or install dominion-flow, the plugin that ships this one along with the rest of its 5 skills, 51 commands, 13 agents.

Wrote 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.

agentmods badge for fire-project-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/thierryn/fire-flow/fire-project-researcher.svg)](https://agentmods.dev/agents/thierryn/fire-flow/fire-project-researcher)
Your own site
<a href="https://agentmods.dev/agents/thierryn/fire-flow/fire-project-researcher"><img src="https://agentmods.dev/badge/agents/thierryn/fire-flow/fire-project-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,000 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00020 $0.01000
Opus 5 $0.00010 $0.00500
Sonnet 5 $0.00004 $0.00200
Haiku 4.5 $0.00002 $0.00100

Measured 7d ago against content hash 9c7ef37cc8d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

fire-project-researcher 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -rl "{focus_keywords}" ~/.claude/plugins/dominion-flow/skills-library/ | head -20
agents/fire-project-researcher.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fire Project Researcher Agent

<command_wiring>

Command Integration

This agent is spawned by:

  • fire-1-new (new project) — 4 parallel instances explore the project's domain before roadmap creation
  • fire-new-milestone (new milestone) — 4 parallel instances research the milestone's scope

Each instance receives a <focus> tag specifying its research domain. The agent writes its findings directly to a file and returns a completion signal.

</command_wiring>


Configuration

name: fire-project-researcher
type: autonomous
color: purple
description: Parallel domain researcher for project initialization
tools:
  - Read
  - Write
  - Glob
  - Grep
  - Bash
  - WebSearch
  - WebFetch
allowed_references:
  - "@skills-library/"
  - "@.planning/"
  - "@docs/"

Focus Areas

Each of 4 parallel instances receives ONE of these:

Instance Focus Output File Researches
1 stack .planning/research/01-stack.md Languages, frameworks, dependencies, build tools, runtime requirements
2 features .planning/research/02-features.md Core features to build, user stories, acceptance criteria, feature dependencies
3 ecosystem .planning/research/03-ecosystem.md Third-party APIs, services, integrations, hosting, databases, auth providers
4 patterns .planning/research/04-patterns.md Design patterns, architecture decisions, skills library matches, anti-patterns to avoid

Process

Step 1: Receive Research Brief

Read the research context provided by the spawning command:

  • Project description / milestone objectives
  • Technology constraints (from user discussion)
  • Scope boundaries

Read the full file on GitHub · 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. 7d ago First seen · 156 lines · 20 tokens per session scan B 9c7ef37cc8d4

Subscribe to this mod's changes

fire-project-researcher is an agent published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 24d ago), licensed MIT. It adds 20 tokens to every session and 1,000 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.

Related

Other agents, from other repositories

spec-miner

Extracts behavioral specs from existing codebases for OpenSpec. Produces flat Requirement and Invariant blocks with structured metadata (entities, enforced, id, test anchors). Outputs openspec/specs/ /spec.md. Fully self-bootstrapping — no dependency on codebase-onboarding. Use when onboarding a brownfield project to…

affaan-m/ECC · 76 tokens

swift-build-resolver

Swift/Xcode build, compilation, and dependency error resolution specialist. Fixes swift build errors, Xcode build failures, SPM dependency issues, and code signing problems with minimal changes. Use when Swift builds fail.

affaan-m/ECC · 48 tokens

security-reviewer

Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.

affaan-m/ECC · 52 tokens

network-architect

Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.

affaan-m/ECC · 31 tokens

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

amend-extractor

Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).

closedloop-ai/claude-plugins · 23 tokens