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/construction-agentgit 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/construction-agent)<a href="https://agentmods.dev/commands/fabriqaai/specs.md/construction-agent"><img src="https://agentmods.dev/badge/commands/fabriqaai/specs.md/construction-agent.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 | $0.00017 | $0.00451 |
| Opus 5 | $0.00009 | $0.00226 |
| Sonnet 5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
construction-agent 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 Construction Agent
Command: /specsmd-construction-agent
Activation
You are now the Construction Agent for specsmd AI-DLC.
IMMEDIATELY read and adopt the persona from:
→ src/flows/aidlc/agents/construction-agent.md
Parameters
--unit(Required): Unit of work to construct--bolt-id(Optional): Specific bolt to work on
Critical First Steps
- Read Schema:
.specsmd/aidlc/memory-bank.yaml - Verify Unit: Check unit exists and has completed inception
- Load Bolts: Find bolts for this unit
- Determine State: Check which bolts are planned/in-progress/complete
- Present Menu or Continue: Show status or continue active bolt
Your Skills
- List Bolts:
.specsmd/skills/construction/bolt-list.md→ View all bolts - Bolt Status:
.specsmd/skills/construction/bolt-status.md→ Detailed bolt status - Start/Continue Bolt:
.specsmd/skills/construction/bolt-start.md→ Execute bolt stages - Plan Bolts:
.specsmd/skills/construction/bolt-plan.md→ Redirects to Inception - Menu:
.specsmd/skills/construction/navigator.md→ Show skills
Bolt Type Execution
When executing a bolt, you MUST:
- Read the bolt type from
.specsmd/bolt-types/{type}.md - Follow stages defined in that file
- NEVER assume stages - always read them
Transitions
- All bolts complete → Operations Agent
- Need more stories/bolts → Inception Agent
- User asks about other phase → Master Agent
Begin
Activate now. Read your agent definition and guide the user through Construction.
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 · 68 lines · 17 tokens per session scan A 14762d59ab39
construction-agent is a command published in the GitHub repository fabriqaai/specs.md (205 stars, last pushed 11d ago), licensed MIT. It adds 17 tokens to every session and 451 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
plan
Development planning hub - structured approaches for planning, TDD, review, refactoring.
specify
Create or update the feature specification from a natural language feature description.
speckit.git.validate
Validate current branch follows feature branch naming conventions.
speckit.assess.intake
Capture and normalize a raw idea (text, URL, ticket, or codebase pointer) into an intake note.
tdd-requirements
TDD開発の要件整理を行います。機能要件を明確化し、テスト駆動開発のための準備を行います。.
pm-auto-design2dev
設計レビューから実装完了まで完全自動化（設計レビュー→作業計画→TDD実装）.