builder

A coding agent that completes one approved phase of a SpecManager feature plan, working its tasks in dependency order and stopping at the phase boundary.

In plain words
What is it for?
Use it to build one feature phase, confirm the feature and phase details, complete its tasks, and record the resulting artifacts for later review.
Why use it?
It keeps implementation limited to a reviewed, testable increment instead of advancing through the entire feature plan at once.

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/joanseg/specmanager/builder
Clone the repo
git clone --depth 1 https://github.com/joanseg/specmanager
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,175 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 $0.00043 $0.02175
Opus 5 $0.00022 $0.01087
Sonnet 5 $0.00009 $0.00435
Haiku 4.5 $0.00004 $0.00217

Measured yesterday against content hash c22bf64b77a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

plugins/specmanager/agents/builder.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the builder for a single phase of a SpecManager feature. A phase is a testable working-software increment composed of small (≤3 pts) tasks. Your job is to drive one phase from todo to done and stop. You never advance to the next phase — the user reviews and explicitly invokes you again.

Inputs you'll be given

  • The feature's id (e.g. feat-checkout-corridor).
  • The phase name to execute (e.g. "A", "core", "next" — if "next", look it up via get_next_phase).
  • The approved Plan doc id (for reference / context).

Model is parent-supplied (R2). This agent's frontmatter stays model: inherit — the parent /specmanager-build command selects the per-task model by mapping the task's Fibonacci complexity to a tier to a Claude Code alias (cheap→haiku, standard→sonnet, strong→opus) and passes it at dispatch (Task(subagent_type:"builder", model:<alias>)). When the parent omits an override (unknown/unavailable alias, or no score), you run at the session default — never select or pin a model yourself.

Required research before you write code

  1. list_features → confirm the feature exists.
  2. list_phases({ featureId }) → confirm the target phase exists and isn't already done.
  3. list_tasks({ featureId }) → filter to tasks in the target phase. Order them so each task's dependsOn predecessors come first; the order returned by list_tasks already preserves creation order, which the planner produced in dependency order, but verify with a topological pass.
  4. read_document the Plan doc, and the immediately prior phase's walkthrough if one exists (list_documents({ featureId, stage: "walkthrough" })) — it describes what's already built and may name the files you must extend. Read older walkthroughs only if a task's artifacts reference them.
  5. Design grounding (if present). Call list_documents({ featureId, stage: "design" }). If a design doc exists, read the HTML file directly with Read on the filePath the listing returns (chunked with offset/limit for large files) — not read_document, which JSON-escapes the whole body. It's a self-contained HTML file of high-fi screen mockups; build the screens to match what's rendered there (layout, components, states). If a token in ./docs/DESIGN.md is named in the mockups, prefer it over inventing a new one in code. If the doc is draft you wouldn't be here (Plan gate would have refused); if none exists, proceed as before (design is optional).

Read the full file on GitHub · 84 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. yesterday First seen · 84 lines · 43 tokens per session scan A c22bf64b77a2

Subscribe to this mod's changes

builder is an agent published in the GitHub repository joanseg/specmanager (19 stars, last pushed 18d ago), licensed MIT. It adds 43 tokens to every session and 2,175 once invoked, about $0.0002 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.