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-2-plangit 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-2-plan)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-2-plan"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-2-plan.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 | $0.00012 | $0.08616 |
| Opus 5 | $0.00006 | $0.04308 |
| Sonnet 5 | $0.00002 | $0.01723 |
| Haiku 4.5 | $0.00001 | $0.00862 |
Grade A, and why
fire-2-plan 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 4d 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 — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-2-plan
Plan phase N with skills library integration and WARRIOR validation
Purpose
Create detailed execution plans for a specified phase by combining Dominion Flow's structured planning with skills library access, honesty protocols, and validation requirements. Plans are reviewed by a plan-checker before approval.
Arguments
arguments:
phase_number:
required: true
type: integer
description: "Phase number to plan (e.g., 1, 2, 3)"
example: "/fire-2-plan 3"
optional_flags:
--gaps: "Plan only for gaps identified in verification"
--research-first: "Force research phase before planning"
--skip-checker: "Skip plan-checker validation (not recommended)"
Process
Step 0.5: Prompt Enhancer — Codebase Convention Scan (v11.0)
conventions BEFORE planning enriches the planner's context with actual patterns, reducing hallucinated approaches and increasing plan accuracy.
Before any validation or planning, scan the project for conventions that should inform the planner:
SCAN (quick — max 60 seconds):
1. Package manager: check for bun.lockb / pnpm-lock.yaml / yarn.lock / package-lock.json
2. Test framework: grep for jest.config / vitest.config / playwright.config / .mocharc
3. Naming patterns: sample 3 source files — camelCase vs snake_case, barrel exports
4. Error handling: grep for common error patterns (try/catch, .catch, Result types)
5. API style: check for REST routes / GraphQL schema / tRPC routers
6. State management: grep for zustand / redux / context / signals
OUTPUT — codebase_conventions block injected into planner context:
<codebase_conventions>
package_manager: {bun | pnpm | yarn | npm}
test_framework: {jest | vitest | playwright | none detected}
naming: {camelCase | snake_case | mixed}
error_pattern: {try-catch | Result type | .catch chains}
api_style: {REST | GraphQL | tRPC | mixed}
state: {zustand | redux | context | none detected}
notes: [any other conventions discovered]
</codebase_conventions>
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.
- 4d ago First seen · 557 lines · 12 tokens per session scan A 7982744cde0e
fire-2-plan is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 22d ago), licensed MIT. It adds 12 tokens to every session and 8,616 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.
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.
requirement-review
需求文档多角色评审(requirement-review):需求文档 → 7-Agent 并行评审 → 重构高质量需求文档(Runtime 受控流程,0-7 阶段状态机).