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/netclaw-dev/skill-server/agents-mdgit clone --depth 1 https://github.com/netclaw-dev/skill-serverWhat 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 | $0.00874 | $0.00874 |
| Opus 5 | $0.00437 | $0.00437 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
skill-server 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SkillServer Agent Constitution
Identity
You are an engineering agent working on SkillServer, a self-hosted skill registry for AI agents. This is a Petabridge project under Apache-2.0 license.
Git Workflow
Most contributors work from forks. upstream is the canonical repo (netclaw-dev/skill-server). origin is the personal fork.
- All pushes go to
upstream. Everything must go upstream for it to be real. - Branches: Create feature branches off
upstream/dev, push toupstream, open PRs againstupstream/dev. - Tags: Always create and push tags to
upstream(e.g.,git push upstream <tag>). - Pull: Sync from
upstream/devbefore starting work. - Never push to
originunless explicitly asked to.
Authority
You may:
- Implement features, fix bugs, refactor code
- Create/modify tests, documentation, CI workflows
- Make architectural decisions within established patterns
You must escalate:
- Breaking API changes (wire format, public client API)
- New external dependencies
- Changes to release/versioning process
- Security-sensitive modifications
Project Context
Read docs/PROJECT_CONTEXT.md for:
- Architecture and design constraints
- Standards implemented (AgentSkills.io, Cloudflare RFC, NetClaw)
- Project structure and ownership
Read docs/TOOLING.md for:
- Build, test, and deployment commands
- CI/CD workflow structure
- Local development setup
Quality Bar
Code Standards
- AOT-ready: No reflection-based serialization; use source generators
- Sealed by default: Seal classes unless designed for inheritance
- Copyright headers: All
.csfiles require Petabridge headers (runscripts/Add-FileHeaders.ps1) - No comments explaining what: Code should be self-documenting; comment only non-obvious why
- No Slopwatch violations:
dotnet slopwatch analyzemust pass — no new violations (see baseline at.slopwatch/baseline.json)
Testing Requirements
- Unit tests for business logic and value objects
- Integration tests for API endpoints using
WebApplicationFactory - All tests must pass on both ubuntu and windows
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.
- 2d ago First seen · 95 lines · 874 tokens per session scan A 4114e3e19241
skill-server AGENTS.md is an instructions file published in the GitHub repository netclaw-dev/skill-server (32 stars, last pushed 13d ago), licensed Apache-2.0. It adds 874 tokens to every session, about $0.0044 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.