fire-researcher

fire-researcher is an agent for coding agents from ThierryN/fire-flow. It costs 15 tokens per session (5,408 once invoked), scanned A, original, MIT.

A research agent that investigates unfamiliar technical topics and problem areas using a library of skills and matching patterns.

In plain words
What is it for?
Use it to research a bug, technology choice, root cause, or alternative implementation and record the findings in a RESEARCH.md file.
Why use it?
It fills knowledge gaps before debugging, planning, verifying, or recovering from a failed plan. This helps an agent make decisions using documented findings instead of guesses.

Agent

Part of the dominion-flow plugin — 5 skills, 51 commands, 15 agents shipped together

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

Or install dominion-flow, the plugin that ships this one along with the rest of its 5 skills, 51 commands, 15 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-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/thierryn/fire-flow/fire-researcher.svg)](https://agentmods.dev/agents/thierryn/fire-flow/fire-researcher)
Your own site
<a href="https://agentmods.dev/agents/thierryn/fire-flow/fire-researcher"><img src="https://agentmods.dev/badge/agents/thierryn/fire-flow/fire-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,408 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00015 $0.05408
Opus 5 $0.00008 $0.02704
Sonnet 5 $0.00003 $0.01082
Haiku 4.5 $0.00002 $0.00541

Measured 5d ago against content hash 54acf6d4c8c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

fire-researcher 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 5d 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.

agents/fire-researcher.md · 791 lines

How it starts

The opening of the file, as written. The whole thing — 791 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fire Researcher Agent

<command_wiring>

Command Integration

This agent is spawned by the following commands:

  • fire-debug (research phase) — When a debug session identifies knowledge gaps that require deeper investigation before a fix can be applied. The debugger spawns a researcher to explore the problem domain.
  • fire-2-plan (technology research) — When the planner encounters unfamiliar technologies or needs to evaluate implementation options. The planner spawns a researcher to produce a RESEARCH.md before creating the plan.
  • fire-planner (recovery research, v11.2) — When a plan fails execution or verification, the planner spawns a researcher to find ALTERNATIVE approaches before re-planning. The researcher returns 2-3 ranked alternatives with confidence scores.
  • fire-4-verify (gap research) — When the verifier identifies gaps, a researcher can be spawned to investigate root causes and alternative implementations before gap closure.

When spawned by these commands, the researcher receives context about what specifically needs to be researched and delivers findings back as a RESEARCH.md document.

Recovery Research Mode (v11.2)

When spawned for recovery (after execution/verification failure), the researcher receives:

  • The failed BLUEPRINT.md (what was attempted)
  • The VERIFICATION.md or error output (what went wrong)
  • The RECORD.md (what was actually built before failure)
Stuck Report Input Format (v12.0 — interface contract)

When spawned from a stuck executor (via articulation protocol), the researcher additionally receives a STUCK REPORT with this structure:

## STUCK REPORT — Task {N}
**Goal:** {what the executor was trying to accomplish}
**Stuck type:** {TRANSIENT | FIXATION | CONTEXT_OVERFLOW | SEMANTIC | DEAD_END | SCOPE_DRIFT}
**Approaches tried:**
  1. {approach} → Expected: {X} → Got: {Y}
  2. {approach} → Expected: {X} → Got: {Y}
**Current constraint:** {what is physically preventing progress}
**What assumption might be wrong:** {honest assessment}
**Confidence this approach is fundamentally viable:** {H/M/L + reason}

Read the full file on GitHub · 791 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. 5d ago First seen · 791 lines · 15 tokens per session scan A 54acf6d4c8c9

Subscribe to this mod's changes

fire-researcher is an agent published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 23d ago), licensed MIT. It adds 15 tokens to every session and 5,408 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.

Related

Other agents, from other repositories

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

dynamic-agents

Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.

VoltAgent/voltagent · 0 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

seo-meta-optimizer

Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.

echoVic/blade-code · 39 tokens

answered-questions-subagent

Processes answered questions from plan.json and incorporates them into relevant tasks.

closedloop-ai/claude-plugins · 19 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens