build-feature

build-feature is a skill for Claude Code, Codex from andrewvaughan/agent-council. It costs 52 tokens per session (3,904 once invoked), scanned A, original, MIT.

A workflow for building a complete software feature across the database, server-side API, user interface, and automated tests. It follows an approved implementation plan or a clearly defined set of tasks.

In plain words
What is it for?
Use it for full-stack work, such as adding stored data, API endpoints, interface components, and tests for one feature.
Why use it?
It helps coordinate the different parts of a feature so they are built and tested together instead of being handled as disconnected changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it for full-stack work, such as adding stored data, API endpoints, interface components, and tests for one feature.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andrewvaughan/agent-council/build-feature
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.

Any agent
npx skills add andrewvaughan/agent-council --skill build-feature
Clone the repo
git clone --depth 1 https://github.com/andrewvaughan/agent-council

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for build-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrewvaughan/agent-council/build-feature/github.svg)](https://agentmods.dev/skills/andrewvaughan/agent-council/build-feature)
Your own site
<a href="https://agentmods.dev/skills/andrewvaughan/agent-council/build-feature"><img src="https://agentmods.dev/badge/skills/andrewvaughan/agent-council/build-feature/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for build-feature

Your own site · 80×15
<a href="https://agentmods.dev/skills/andrewvaughan/agent-council/build-feature"><img src="https://agentmods.dev/badge/skills/andrewvaughan/agent-council/build-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,904 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00052 $0.03904
Opus 5 $0.00026 $0.01952
Sonnet 5 $0.00010 $0.00781
Haiku 4.5 $0.00005 $0.00390

Measured 10d ago against content hash 98f42107aa67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

build-feature 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 10d 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.

canonical/skills/build-feature/SKILL.md · 443 lines

How it starts

The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full-Stack Feature Implementation Workflow

Execute a full-stack feature implementation across database, backend, frontend, and testing layers. This skill follows the implementation plan produced by /plan-feature and builds all layers with integrated testing.

[!CAUTION] Scope boundary: This skill implements code and commits it. It does NOT create pull requests, push to remote, run code reviews, or submit anything for merge. When implementation and commits are complete, stop and suggest the user run /review-code next. Do not proceed to PR creation — that is /submit-pr's job.

Step 1: Load Implementation Plan

Check for an implementation plan using the following priority:

[!NOTE] GitHub issues created by /plan-feature are task-oriented work items — the decision record remains the authoritative source of council evaluations, rationale, and architectural context. When loading from an issue, always read the referenced decision record for full context.

Option A: GitHub Issue (Primary)

If the user provides a GitHub issue number (e.g., /build-feature 42 or /build-feature #42):

  1. Fetch the issue details:

    gh issue view <number> --json title,body,labels,state,number
    
  2. Validate the issue:

    • Confirm it has the build-ready label (warn if not — it may not have been through /plan-feature or may need further planning)
    • If the issue is closed, warn the user and ask whether to proceed
  3. Parse the issue body to extract:

    • Implementation Plan: Task checkboxes organized by layer (Frontend, Backend, Database, Testing)
    • Technical Context: Architecture decisions, API contracts, schema changes
    • Decision Record path: Read the referenced decision record for full council context
    • Feature Flag: Flag name if applicable
    • Success Metrics: Measurable outcomes
  4. Read the referenced decision record from the path specified in the issue for complete council rationale.

  5. Signal work is in progress (see AGENTS.md "Label Management" for rules):

Read the full file on GitHub · 443 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. 10d ago First seen · 443 lines · 52 tokens per session scan A 98f42107aa67

Subscribe to this mod's changes

build-feature is a skill published in the GitHub repository andrewvaughan/agent-council (13 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 3,904 once invoked, about $0.0003 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.