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/using-8-habits)<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/using-8-habits"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/using-8-habits/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/using-8-habits"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/using-8-habits.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 | $0.00067 | $0.02626 |
| Opus 5 | $0.00034 | $0.01313 |
| Sonnet 5 | $0.00013 | $0.00525 |
| Haiku 4.5 | $0.00007 | $0.00263 |
Grade A, and why
using-8-habits 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using 8-Habit AI Dev (คู่มือเริ่มต้น)
Habit: H5 (Seek First to Understand — read before acting) + H8 (Find Your Voice — empower the next person)
Purpose: First skill to invoke when you're new to 8-habit-ai-dev, or when you're unsure which skill fits your current task. Explains the 7-step workflow, all 24 skills, and provides a decision tree for "which skill next?". When invoked with an argument (a free-text intent like /using-8-habits "I need to verify what we built last week"), switches to ranked-recommendation mode — see Smart-routing mode below.
When to Use This Skill
- First time using the plugin — start here
- Unsure which skill to invoke for your current task
- Onboarding a new team member or AI agent to the plugin
- Wanting a refresher on the 7-step workflow
- Deciding whether to skip a step (and needing the honest skip rules)
When to Skip
- You already know exactly which skill you need → invoke it directly
- You're in the middle of an established workflow (e.g. already did
/requirements, going to/design) — the skill itself will tell you what comes next via thenext-skillfrontmatter field
The Core 5 (80/20 rule)
Most tasks only need these 5 skills:
/requirements— define what "done" looks like before coding (H2)/review-ai— audit AI-generated code before committing (H4)/cross-verify— 17-question 8-habit checklist before shipping (H1–H8)/research— investigate before specifying when the problem is new (H5)/reflect— 5-question micro-retrospective after completing significant work (H7)
The other 19 skills are optional depth for specific situations — architecture-heavy work (/design), operational finding classification (/operational-state), transparency logs (/ai-dev-log), onboarding (this skill), etc. EU AI Act compliance migrated to pitimon/claude-governance v3.1.0 (see ADR-012); install that plugin alongside this one for the canonical /eu-ai-act-check. Running all 24 skills for every task is theater. Pick what fits.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 174 lines · 67 tokens per session scan A 0f1dc4205e9b
using-8-habits is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 2,626 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 2026-08-31.
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.