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 instructions/helderberto/agent-skills/agents-mdgit clone --depth 1 https://github.com/helderberto/agent-skillsWrote 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/instructions/helderberto/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/helderberto/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/helderberto/agent-skills/agents-md.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 | $0.01509 | $0.01509 |
| Opus 5 | $0.00754 | $0.00754 |
| Sonnet 5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
agent-skills AGENTS.md 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 3d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (Claude Code, Cursor, Gemini CLI, OpenCode, Copilot, etc.) when working with this repository.
Repository Overview
helderberto/agent-skills is a personal SDLC toolbelt for AI coding agents. Skills are packaged Markdown instructions that extend agent capabilities across the full lifecycle — from spec to ship.
Project Structure
skills/ → Core skills (one folder per skill, each with SKILL.md)
agents/ → Subagent definitions the skills fan out to (Claude Code only)
docs/ → Setup guides per agent (Cursor, Gemini CLI, OpenCode, Copilot)
.claude-plugin/ → Plugin manifest + marketplace entry (Claude Code)
Integration Model
Different agents discover skills through different mechanisms. This repo supports all of them through one source of truth — the skills/ directory.
| Agent | Discovery mechanism |
|---|---|
| Claude Code | Plugin marketplace (/plugin install hb@helderberto-skills) |
| Gemini CLI | gemini skills install from this repo |
| OpenCode | Auto-routes via this AGENTS.md + the skill tool |
| Cursor | Copy skills into .cursor/rules/ or reference via .cursorrules |
See docs/ for per-agent setup instructions.
OpenCode Integration
OpenCode uses a skill-driven execution model — the agent reads this file plus the skills/ directory and auto-routes user intent to the right skill.
Core Rules
- If a task matches a skill, you MUST invoke it
- Skills live at
skills/<skill-name>/SKILL.md - Never implement directly when a skill applies
- Always follow the skill instructions exactly — do not partially apply them
Intent → Skill Mapping
| User intent | Skill to invoke |
|---|---|
| New feature with unclear requirements | spec → plan → build |
| Implement next phase of a plan | build |
| Verify work + check plan progress | test |
| Test-first development | tdd |
| Implement using official docs | source-driven |
| Research a question against sources | research |
| Bug, error, unexpected behavior | diagnose |
| Backfill tests / split large functions | fortify |
| Simplify code without changing behavior | code-simplify |
| Design or improve a module's interface | codebase-design |
| Architectural friction in codebase | architecture-audit |
| Prototype a design (terminal app or UI) | prototype |
| Explain code or codebase area | explain-code |
| Code review on a PR | code-review |
| Visual/HTML PR review (annotated diff) | visual-review |
| Triage existing PR review comments (what to fix) | triage-review |
| Reply to PR review comment | pr-reply |
| Check accessibility | a11y-audit |
| Check i18n coverage | i18n |
| Audit bundle size / performance | perf-audit |
| Audit dependencies for CVEs | deps-audit |
| Check for sensitive data in repo | safe-repo |
| Run linter / formatter | lint |
| Run the test suite | testing |
| Validate code (lint + types + tests) | validate-code |
| Write end-to-end tests (Cypress) | e2e |
| Commit changes (atomic, grouped by concern) | commit |
| Commit and push | ship |
| Create a pull request | create-pull-request |
| Record an architectural decision | create-adr |
| Pin down domain terminology / glossary | domain-modeling |
| Set up pre-commit hooks | setup-pre-commit |
| Stress-test a plan or design | grill-me |
| Fix prose / typos in markdown | prose-fix |
| Restructure an article draft | revise |
| Hand off mid-session work to a fresh agent | handoff |
| Author a new skill | create-skill |
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.
- 3d ago First seen · 108 lines · 1,509 tokens per session scan A 64edeacc008b
agent-skills AGENTS.md is an instructions file published in the GitHub repository helderberto/agent-skills (13 stars, last pushed 2d ago), licensed MIT. It adds 1,509 tokens to every session, about $0.0075 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.
Other instructions, from other repositories
Skillry AGENTS.md
AGENTS.md instructions for FluxonLab/Skillry, covering agents.md, operating model, core engineering principles, evidence, research, and verification and scope, plans, and decisions.
Skillry CLAUDE.md
Claude Code instructions for FluxonLab/Skillry, covering claude.md, operating model, core engineering principles, evidence, research, and verification and scope, plans, and decisions.
aiworkspace AGENTS.md
Instructions for a-tokyo/aiworkspace, covering ai workspace, structure, key commands, conventions and code quality.
instancez CLAUDE.md
Claude Code instructions for instancez/instancez, a project described as: An LLM-friendly, single-binary, drop-in replacement to Supabase.
P0G AGENTS.md
Instructions for yz9yt/P0G, covering p0g agent guidelines, core principles, 1. clean instance mindset, 2. explicit over implicit and 3. minimal footprint.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).