build-brief

build-brief is a skill for Claude Code from pitimon/8-habit-ai-dev. It costs 40 tokens per session (1,579 once invoked), scanned A, original, MIT.

A context-rich implementation brief prepared before coding, after the work has been broken into tasks.

In plain words
What is it for?
Use it to prepare focused work items for features, fixes, or other changes in an existing codebase.
Why use it?
It makes the problem, existing code, project conventions, and relevant past lessons clear before new code is written.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the 8-habit-ai-dev plugin — 24 skills, 2 agents, 1 hook shipped together

Good fit Use it to prepare focused work items for features, fixes, or other changes in an existing codebase.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add pitimon/8-habit-ai-dev
Claude Code
/plugin install 8-habit-ai-dev

Made for: Claude Code.

Or install 8-habit-ai-dev, the plugin that ships this one along with the rest of its 24 skills, 2 agents, 1 hook.

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-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/build-brief/github.svg)](https://agentmods.dev/skills/pitimon/8-habit-ai-dev/build-brief)
Your own site
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/build-brief"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/build-brief/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-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/build-brief"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/build-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,579 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 $0.00040 $0.01579
Opus 5 $0.00020 $0.00790
Sonnet 5 $0.00008 $0.00316
Haiku 4.5 $0.00004 $0.00158

Measured 9d ago against content hash 64b28f11e174, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

build-brief 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 9d 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.

plugin/skills/build-brief/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Step 4: Build (บรีฟให้ชัด ไม่ใช่แค่สั่ง)

Habit: H5 — Seek First to Understand | Anti-pattern: Prompting "build X" without reading existing code

Process

  1. Problem statement gate (REQUIRED before anything else):

    "What specific problem does this implementation solve?"

    Must cite one of: requirement (issue #), bug report, or design decision (ADR). If you cannot answer this question, go back to /requirements first.

    Research basis: Amazon Working Backwards, Basecamp Shape Up, and Google Design Docs all physically separate "what & why" from "how". Teams that skip this waste 30-40% of implementation time on rework.

  2. Read existing code and context first: Before writing anything new, read the files in the affected area. Also read repo context files when present: DOMAIN.md, SPEC.md, CONTEXT.md, CONTEXT-MAP.md, docs/agents/domain.md, and relevant ADRs. Understand current patterns, naming conventions, glossary terms, and architecture.

1b. Check past lessons (if ~/.claude/lessons/ exists):

  • Grep ~/.claude/lessons/ for tags or keywords matching the task name, affected file paths, or domain
  • Search by tags first: Grep pattern="tags:.*<keyword>" path="~/.claude/lessons/"
  • Fall back to keyword search: Grep pattern="<keyword>" path="~/.claude/lessons/"
  • If relevant lessons found, include them in the context brief under "Lessons from past work"
  • If no lessons directory or no matches, skip silently
  1. Build the context brief:

    ## Implementation Brief: [Task Name]
    **Goal**: [1 sentence]
    **Files to modify**: [list with paths]
    **Existing patterns to follow**: [e.g., "uses callRemoteAPI + wrapSuccess pattern"]
    **Project vocabulary**: [canonical terms from CONTEXT.md / DOMAIN.md, if present]
    **Constraints**: [e.g., "must be backward compatible", "max 800 lines"]
    **Test approach**: [what to test, TDD if applicable]
    

    If the user requested TDD, red-green-refactor, or test-first work, load ${CLAUDE_PLUGIN_ROOT}/guides/tdd-tracer-bullet.md and define the first behavior-level tracer bullet before implementation starts.

Read the full file on GitHub · 132 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. 9d ago First seen · 132 lines · 40 tokens per session scan A 64b28f11e174

Subscribe to this mod's changes

build-brief is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,579 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 2026-08-31.