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-scaffoldgit 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-scaffold)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-scaffold"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-scaffold.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 | $0.00011 | $0.02345 |
| Opus 5 | $0.00005 | $0.01172 |
| Sonnet 5 | $0.00002 | $0.00469 |
| Haiku 4.5 | $0.00001 | $0.00234 |
Grade A, and why
fire-scaffold 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-scaffold
Create a feature or component the right way — guided wizard, consistent output
Purpose
Scaffold individual features and components within an active phase using a guided multi-step wizard. Fills the gap between high-level phase plans (BLUEPRINT.md) and ad-hoc feature creation.
Why this command exists: Phase planning scopes WHAT to build. Scaffolding guides HOW to build it consistently — same structure, same conventions, every time.
Arguments
arguments:
type:
required: false
type: string
choices: [component, endpoint, model, page, hook, service, test, custom]
description: "What to scaffold (prompted if not provided)"
example: "/fire-scaffold component"
optional_flags:
--name: "Pre-fill the name (will prompt if not provided)"
--phase: "Phase number to add this to (defaults to current phase)"
--dry-run: "Show generated files without writing them"
--minimal: "Skip optional steps, use smart defaults"
Wizard Step Sequence
graph LR
S1[1: Type Selection] --> S2[2: Naming]
S2 --> S3[3: Location]
S3 --> S4[4: Dependencies]
S4 --> S5[5: Behavior Config]
S5 --> S55[5.5: Preview]
S55 --> S6[6: Generate + Confirm]
LLM step adherence. LLMREI (arXiv 2507.02564) — 5-step interview protocol. Clack group() (7.4k★) — results-passing between steps for conditional branching.
Process
Step 1: Type Selection
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
DOMINION FLOW ► SCAFFOLD
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
What are you creating?
1. React Component - UI component with props, state, tests
2. API Endpoint - Route handler, validation, error responses
3. Database Model - Schema, migrations, type definitions
4. Page - Full route page with layout, data loading
5. Custom Hook - Reusable React hook with tests
6. Service/Module - Business logic module with interface
7. Test Suite - Test file for an existing module
8. Custom - Describe it — I'll derive the scaffold
> [User selection]
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 · 298 lines · 11 tokens per session scan A 188f61e8c1cb
fire-scaffold is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 22d ago), licensed MIT. It adds 11 tokens to every session and 2,345 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）.