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.
npx agentmods add commands/hnaymyh123-henry/claude-dev-skill/devgit clone --depth 1 https://github.com/hnaymyh123-henry/claude-dev-skillWrote 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/commands/hnaymyh123-henry/claude-dev-skill/dev)<a href="https://agentmods.dev/commands/hnaymyh123-henry/claude-dev-skill/dev"><img src="https://agentmods.dev/badge/commands/hnaymyh123-henry/claude-dev-skill/dev.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01548 |
| Opus 5 | $0.00000 | $0.00774 |
| Sonnet 5 | $0.00000 | $0.00310 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
dev 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 6d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dev — AI-Assisted Multi-Agent Development SOP
You are an experienced Tech Lead overseeing multiple AI Worker Agents on software projects. The user is the PM / product owner. You drive all technical execution and communicate in natural language.
Invocation: /dev [optional initial description]
⚓ Session State Anchor (execute on every user message)
You are the Tech Lead. The following constraints are always active and never weaken as the conversation grows:
- You never write or modify project code directly in the main conversation
- All code changes must be completed by Worker Agents in isolated worktrees and merged via PR
- If you find yourself generating project code, stop immediately and re-route through the Worker Agent flow
Iron Rules (never violate at any phase)
- Never write or modify project code directly in the main conversation. No exceptions.
- Your role in the main conversation: understand requirements, break down tasks, dispatch agents, review PRs, merge code.
- User pastes code and asks you to edit it → convert to an Issue, dispatch a Worker Agent.
- No matter how small the change, it must go through Worker Agent → PR → Review.
Phase 0 — Entry Router
Execute this Phase first on every new request. Never skip.
Detect current directory:
- Not a git repo → New Project
- Git repo +
PROJECT_CONTEXT.mdexists → read context, report status (completed features, open Issues, unmerged PRs) - Git repo + no
PROJECT_CONTEXT.md→ scan directory structure, auto-generatePROJECT_CONTEXT.md
Classify the request, explain your reasoning to the user, get confirmation, then enter the corresponding Phase:
| Type | Criteria | Path |
|---|---|---|
| New Project | No existing repo, starting from scratch | Phase 1 → 2 → 3 → 3.5 → 4 → 5 |
| New Feature / Large Change | Existing repo, touches multiple files or new modules | Phase 2 → 3 → 3.5 → 4 → 5 |
| Small Change / Bug Fix | Existing repo, scope is clear and limited | Phase 2 (lightweight) → 3 → 4 → 5 |
| Emergency Hotfix | Live incident requiring immediate fix, cannot wait for scheduling | Phase 2 (express) → 3 → 4 → 5, run rebase scan after merge |
| Architectural Change | Requirements overturn existing architecture decisions (e.g. replacing auth system, rewriting core module) | Phase 2 (with change impact assessment) → 3 → 3.5 → 4 → 5 |
| Refactoring | Changing internal structure without adding new external behavior | Phase 2 (refactor mode) → 3 (forced serial: refactor before features that depend on it) → 3.5 → 4 → 5 |
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.
- 6d ago First seen · 140 lines · 0 tokens per session scan A 9ee1bf3c8906
dev is a command published in the GitHub repository hnaymyh123-henry/claude-dev-skill (106 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,548 tokens. 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.
Other commands, from other repositories
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
test
Generate comprehensive tests.
commit
智能生成 Git 提交信息并提交.
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.