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.
npx agentmods add commands/thierryn/fire-flow/fire-1b-researchgit 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-1b-research)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-1b-research"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-1b-research.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 | $0.00017 | $0.01797 |
| Opus 5 | $0.00009 | $0.00898 |
| Sonnet 5 | $0.00003 | $0.00359 |
| Haiku 4.5 | $0.00002 | $0.00180 |
Grade A, and why
fire-1b-research 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 6d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-1b-research
Spawn researchers, select architecture vision, generate roadmap
Purpose
Research the technology landscape, select a coherent architecture, and generate the project roadmap. This is Step 2 of 3 in project initialization.
Flow: /fire-1a-new → /fire-1b-research → /fire-1c-setup
Prerequisite: .planning/PROJECT.md and .planning/REQUIREMENTS.md must exist (created by /fire-1a-new).
EXECUTION ORDER
STEP 1: Validate prerequisites → PROJECT.md + REQUIREMENTS.md exist
STEP 2: Research Synthesis → spawn researchers, search GitHub, write SYNTHESIS.md
STEP 3: Vision Branch Selection → spawn fire-vision-architect, user picks branch, LOCK VISION.md
STEP 4: Roadmap Generation → spawn fire-roadmapper, write ROADMAP.md
FINAL: Chain to next command → tell user to run /fire-1c-setup
Complete each step before starting the next. Each step produces a file — verify it exists before proceeding.
Step 1: Validate Prerequisites
test -f .planning/PROJECT.md && test -f .planning/REQUIREMENTS.md && echo "READY" || echo "MISSING — run /fire-1a-new first"
If files are missing, stop and tell the user to run /fire-1a-new first.
Read .planning/PROJECT.md to determine mode (forward/backward) for Step 3.
Step 2: Research Synthesis (MANDATORY)
Spawn 4 parallel researchers (or sequential if resources are limited):
| Researcher | Focus | Output |
|---|---|---|
| STACK | Technology ecosystem, versions, compatibility | research/STACK.md |
| FEATURES | Feature implementation patterns, complexity | research/FEATURES.md |
| ARCHITECTURE | Folder structure, data flow, API design | research/ARCHITECTURE.md |
| PITFALLS | Common mistakes, known issues, anti-patterns | research/PITFALLS.md |
Every researcher MUST search GitHub for open source reference projects:
Search for 2-3 real open source projects similar to what the user is building:
- Repo name, stars, last updated
- Tech stack used
- Folder structure patterns
- Key patterns worth adopting
- Mistakes visible in their issues/PRs
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.
- 6d ago First seen · 211 lines · 17 tokens per session scan A 31ee520e8419
fire-1b-research is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 23d ago), licensed MIT. It adds 17 tokens to every session and 1,797 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
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
test
Generate comprehensive tests.
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
commit
智能生成 Git 提交信息并提交.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.