skill-engineering AGENTS.md

Repository instructions for creating, testing, maintaining, and releasing agent skills. They also describe the workflow for a self-hosted product that manages those skills.

In plain words
What is it for?
Use them when adding or changing skills, running checks, preparing releases, or working on the self-hosted product. They also define where to begin when resuming work in the repository.
Why use it?
They give contributors shared rules for planning changes, protecting sensitive data, validating skills, and controlling releases. This reduces the chance of inconsistent or unsafe repository changes.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/wukongai/skill-engineering/agents-md
Clone the repo
git clone --depth 1 https://github.com/wukongai/skill-engineering

Made for: Codex, OpenCode.

Per session 422 This file is loaded in full into every session.
When invoked 422 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00422 $0.00422
Opus 5 $0.00211 $0.00211
Sonnet 5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 2d ago against content hash 2322e5bd5aec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-engineering 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 2d 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.

AGENTS.md · 27 lines

How it starts

The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Engineering

Skill Engineering is the standalone source of truth for Agent Skill creation, Doctor, behavior evaluation, continuous maintenance, self-evolution, and release safety.

Rules

  1. Use Simplified Chinese for user-facing collaboration unless the user requests otherwise.
  2. Feature work requires a spec and plan before implementation.
  3. Preview before write; apply must reference the same immutable plan.
  4. Never store credentials, raw sensitive prompts, or full conversations in local state.
  5. Static Doctor scores are structural readiness, not downstream utility.
  6. Candidate generation must not receive holdout assertions or baseline scores.
  7. Canary/Active release requires explicit approval; Global release is out of scope.
  8. Run pytest, Ruff, Skill validation, credential lint, and diff check before declaring completion.

Self-hosted product workflow

  1. For a new capability request, self-check existing Skills/scripts/plugins/docs and complete discovery before choosing an artifact. Do not create product/version scaffolding before deciding that a Skill is needed.
  2. When resuming this existing repository, start with docs/PRODUCT.md, docs/constitution.md, docs/architecture.md, docs/TASK.md, and the current Sprint.
  3. Feature work requires a current file under docs/specs/ and docs/plans/ before implementation.
  4. Cross-version architecture decisions require an ADR under docs/adr/.
  5. New ideas that are not part of the active Sprint go to docs/BACKLOG.md; do not silently expand the current version.
  6. Record daily facts and blockers under docs/logs/daily/; promote stable rules into formal docs instead of citing the log forever.
  7. Update README, Changelog, Roadmap, Task, Sprint, version sources, tests, and release evidence together before a release claim.
  8. Use an isolated candidate and the maintenance engine for changes to Skill Engineering; do not edit maintained Skill source as an experiment.
  9. Commit and push are separate approval points. Never auto-publish, auto-tag, or auto-enable Global scope.

Read the full file on GitHub · 27 lines

Changes

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.

  1. 2d ago First seen · 27 lines · 422 tokens per session scan A 2322e5bd5aec

Subscribe to this mod's changes

skill-engineering AGENTS.md is an instructions file published in the GitHub repository wukongai/skill-engineering (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 422 tokens to every session, about $0.0021 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.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens