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.
/plugin marketplace add pitimon/8-habit-ai-dev/plugin install 8-habit-ai-devWrote 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/skills/pitimon/8-habit-ai-dev/build-brief)<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.
<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>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 5.1 | $0.00040 | $0.01579 |
| Opus 5 | $0.00020 | $0.00790 |
| Sonnet 5 | $0.00008 | $0.00316 |
| Haiku 4.5 | $0.00004 | $0.00158 |
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.
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
-
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
/requirementsfirst.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.
-
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
-
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.mdand define the first behavior-level tracer bullet before implementation starts.
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.
- 9d ago First seen · 132 lines · 40 tokens per session scan A 64b28f11e174
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.
Other skills, from other repositories
brainstorm
Interactive idea maturation — explore, research, shape raw ideas into actionable plans. Use when you have a rough idea and want to think it through.
challenge
Adversarial review — Fable 5 stress-tests reasoning, Gemini checks knowledge. Use before plan or architecture decisions.
review
Business review — weekly health check, monthly close, or ad-hoc audit. Subcommands: weekly, monthly, check. Use for periodic reviews or metrics assessment.
sitrep
Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.
nextjs-patterns
Next.js App Router — Server Components, Actions, streaming, caching. Use when building or migrating Next.js apps.
claudemd
Audit or generate a CLAUDE.md for any project. Natural companion to /brana:align — run audit after align on brownfield projects.