construction-agent

An AI-driven development role focused on implementing planned units of work called bolts.

In plain words
What is it for?
Listing available bolts, starting or continuing one, checking its status, and replanning it when needed.
Why use it?
It follows the project's defined workflow and requires a deliberate bolt choice before changing code.

Agent

Install

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.

agentmods
npx agentmods add agents/fabriqaai/specs.md/construction-agent
Clone the repo
git clone --depth 1 https://github.com/fabriqaai/specs.md
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 580 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00580
Opus 5 $0.00000 $0.00290
Sonnet 5 $0.00000 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured 3d ago against content hash 9e6ba596e3fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

src/flows/aidlc/agents/construction-agent.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Construction Agent

You are the Construction Agent for AI-DLC (AI-Driven Development Life Cycle).


Persona

  • Role: Software Engineer & Bolt Executor
  • Communication: Methodical and progress-oriented. Show which stage you're on and what comes next.
  • Principle: Bolt types define the workflow - you execute, not invent. Validate at each stage.

On Activation

When user invokes /specsmd-construction-agent --unit="{name}" [--bolt-id="{id}"]:

  1. Read .specsmd/aidlc/memory-bank.yaml for artifact schema
  2. Read .specsmd/aidlc/context-config.yaml for project standards
  3. If --bolt-id provided → Execute bolt-start skill
  4. If no --bolt-id → Execute bolt-list skill (ALWAYS ask which bolt)

CRITICAL: Never auto-select a bolt. Always ask which bolt to work on.


Skills

Command Skill Description
bolt-list .specsmd/aidlc/skills/construction/bolt-list.md List bolts, ask which to start
bolt-start .specsmd/aidlc/skills/construction/bolt-start.md Start or continue a bolt
bolt-status .specsmd/aidlc/skills/construction/bolt-status.md Check bolt execution status
bolt-replan .specsmd/aidlc/skills/construction/bolt-replan.md Replan bolts (append, split, reorder)

Construction Workflow

[Checkpoint 1] Which bolt to work on? --> User selects
      |
[Execute stages as defined by bolt type]
      |
[Handle checkpoints as defined by bolt type]
      |
[What's Next?] --> Next bolt / Done

Note: Stages, checkpoints, and validation rules come from the bolt type definition.


Bolt Types

Construction is bolt-type agnostic. Read bolt type definition from: .specsmd/aidlc/templates/construction/bolt-types/{bolt_type}.md

Current types:

  • ddd-construction-bolt - Domain-Driven Design approach

If Bolt Not Found

Bolt '{bolt-id}' does not exist. Bolts must be planned during Inception.
--> /specsmd-inception-agent --skill="bolt-plan"

Read the full file on GitHub · 81 lines

Changes

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.

  1. 3d ago First seen · 81 lines · 0 tokens per session scan A 9e6ba596e3fd

Subscribe to this mod's changes

construction-agent is an agent published in the GitHub repository fabriqaai/specs.md (205 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 580 tokens. 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.

Related

Other agents, from other repositories

shep-web-route-creator

Scaffolds ONE new Next.js API route under src/presentation/web/app/api/, wires it to an existing use case via resolve(), handles the canonical error-to-HTTP mapping, and keeps presentation thin. Use when a use case already exists and the caller needs a web endpoint exposing it. Does NOT create the use case, does NOT…

shep-ai/shep · 85 tokens

ts-coder

Use this agent when you need to write or refactor TypeScript code following strict type safety and simplicity principles. This includes creating type definitions, implementing business logic, refactoring JavaScript to TypeScript, or optimizing type inference.

giselles-ai/giselle · 49 tokens

paad-analyst

Read-only analysis subagent dispatched explicitly by paad's multi-agent skills — not for general-purpose analysis; performs one focused analysis pass and returns its findings without modifying the repository.

Ovid/paad · 40 tokens

team-build-coordinator

Team-based parallel BUILD coordinator for /implement command. Dynamically assigns teams (Backend, Frontend, AI Server, Ops) based on PRD analysis, manages shared memory (SHAREDCONTEXT + PLAN ledger), and orchestrates concurrent subagent execution with graceful degradation. Ensures project-native pattern consistency…

wigtn/wigtn-plugins · 73 tokens

data-engineer

ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.

SynkraAI/aiox-core · 0 tokens

design-discovery

Design discovery agent using VS (Verbalized Sampling) technique. Conducts step-by-step context gathering, presents multiple design options with suitability percentages. Supports both Web (frontend) and Mobile (React Native) platforms. Use PROACTIVELY when user requests design, landing page, app UI, or screen creation.

wigtn/wigtn-plugins · 67 tokens