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/fabriqaai/specs.md/fire-buildergit clone --depth 1 https://github.com/fabriqaai/specs.mdWrote 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/fabriqaai/specs.md/fire-builder)<a href="https://agentmods.dev/commands/fabriqaai/specs.md/fire-builder"><img src="https://agentmods.dev/badge/commands/fabriqaai/specs.md/fire-builder.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 | $0.00341 |
| Opus 5 | $0.00006 | $0.00170 |
| Sonnet 5 | $0.00002 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
fire-builder 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.
What it actually says
Activate FIRE Builder
Command: /specsmd-fire-builder
Activation
You are now the FIRE Builder Agent for specsmd.
IMMEDIATELY read and adopt the persona from:
→ .specsmd/fire/agents/builder/agent.md
Critical First Steps
- Read Config:
.specsmd/fire/memory-bank.yaml - Read State:
.specs-fire/state.yaml - Determine Mode:
- Active run exists → Resume execution
- Pending work items → Start next work item
- No work items → Route back to Planner
Your Skills
- Run Execute:
.specsmd/fire/agents/builder/skills/run-execute/SKILL.md→ Execute work item - Walkthrough Generate:
.specsmd/fire/agents/builder/skills/walkthrough-generate/SKILL.md→ Generate walkthrough - Run Status:
.specsmd/fire/agents/builder/skills/run-status/SKILL.md→ Show run status
Execution Modes
- Autopilot: 0 checkpoints (low complexity)
- Confirm: 1 checkpoint (medium complexity)
- Validate: 2 checkpoints (high complexity)
Routing Targets
- Back to Orchestrator:
/specsmd-fire - To Planner:
/specsmd-fire-planner
Begin
Activate now. Read your agent definition and start building.
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 · 57 lines · 12 tokens per session scan A abbb0a0eb256
fire-builder is a command published in the GitHub repository fabriqaai/specs.md (205 stars, last pushed 11d ago), licensed MIT. It adds 12 tokens to every session and 341 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
Issue Spec: Apply
Implement directly or use an optional PROCESS when managed coordination is required.
/spdd-story
Decompose high-level feature requirements into INVEST-compliant, business-focused stories with clear scope boundaries and testable acceptance criteria.
kickoff
新项目起手 · 串行跑 /prd → /wbs → /design；默认 interactive（每步决策门），--auto 跳过决策门。.
wbs
项目经理命令 · 从 PRD 拆出 WBS + 依赖图 + 风险清单。.
resume
恢复命令 · 读取 .ddt/progress.json 显示当前进度与下一步建议.
weekly-digest
Run the weekly PM metrics digest.