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/borhen68/skillengine/agents-mdgit clone --depth 1 https://github.com/borhen68/SkillEngineWhat 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 | $0.01851 | $0.01851 |
| Opus 5 | $0.00925 | $0.00925 |
| Sonnet 5 | $0.00370 | $0.00370 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
SkillEngine 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 yesterday.
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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
The single source of truth for how AI agents operate within this repository.
This document is loaded into every session. It defines the rules, the mapping from intent to skill, and the orchestration model that makes agents predictable, reliable, and safe. Read it. Follow it. No exceptions.
Repository Overview
This is not a library. It's not a framework. It's a control system for AI agents.
SkillEngine encodes the workflows, quality gates, and decision-making patterns that separate production engineering from prototyping. When an agent follows these skills, it ships code that passes review, survives incidents, and doesn't wake engineers at 3 AM.
What this repository contains:
- 28 skills — step-by-step workflows with checkpoints, anti-rationalization tables, and evidence-based verification
- 5 agent personas — specialist roles (code reviewer, security auditor, test engineer, performance auditor, SRE)
- 5 reference checklists — quick-reference material for testing, security, performance, accessibility, and reliability
- Validation pipeline — automated quality gates that enforce skill anatomy and cross-skill consistency
What this repository demands:
- Skills are mandatory, not optional
- Verification is non-negotiable
- "Seems right" is never sufficient
- Every assumption must be stated
OpenCode Integration
OpenCode uses a skill-driven execution model powered by the skill tool and this repository's /skills directory.
Core Rules
- If a task matches a skill, you MUST invoke it
- Skills are located in
skills/<skill-name>/SKILL.md - Never implement directly if a skill applies
- Always follow the skill instructions exactly (do not partially apply them)
Intent → Skill Mapping
The agent should automatically map user intent to skills:
- Feature / new functionality →
spec-driven-development, thenincremental-implementation,test-driven-development - Planning / breakdown →
planning-and-task-breakdown - Bug / failure / unexpected behavior →
debugging-and-error-recovery - Code review →
code-review-and-quality - Refactoring / simplification →
code-simplification - API or interface design →
api-and-interface-design - UI work →
frontend-ui-engineering - Data pipelines / ETL →
data-engineering - ML model deployment →
ai-ops - Cloud cost concerns →
cost-optimization - Resilience testing →
chaos-engineering
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.
- yesterday First seen · 210 lines · 1,851 tokens per session scan A 18b679a70185
SkillEngine AGENTS.md is an instructions file published in the GitHub repository borhen68/SkillEngine (17 stars, last pushed 2mo ago), licensed MIT. It adds 1,851 tokens to every session, about $0.0093 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
addyosmani-agent-skills-zh AGENTS.md
Instructions for vinvcn/addyosmani-agent-skills-zh, covering agents.md, 仓库概览, opencode 集成, 核心规则 and 意图 → skill 映射.
addyosmani-agent-skills-zh CLAUDE.md
Instructions for vinvcn/addyosmani-agent-skills-zh, covering agent-skills, 项目结构, 按阶段划分的 skills, 约定 and 命令.
agent-skills CLAUDE.md
Instructions for addyosmani/agent-skills, covering agent-skills, project structure, skills by phase, conventions and contributing.
agent-skills AGENTS.md
Instructions for addyosmani/agent-skills, covering agents.md, repository overview, opencode integration, core rules and intent → skill mapping.
agent-skills AGENTS.md
Instructions for helderberto/agent-skills, covering agents.md, repository overview, project structure, integration model and opencode integration.
ai-agent-skills AGENTS.md
Instructions for DevelopersGlobal/ai-agent-skills, covering ai agent instructions for this repository, when working in this repository, repository structure, key principles and when adding a new skill.