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/harbor-framework/skills/agents-mdgit clone --depth 1 https://github.com/harbor-framework/skillsWhat 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 | $0.00651 | $0.00651 |
| Opus 5 | $0.00326 | $0.00326 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
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 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
harbor-skills — Agent Quick Reference
Agent Skills for the Harbor framework. Skills follow the Agent Skills open standard.
Skill Format Quick Reference
Each skill lives in skills/<skill-name>/ with a required SKILL.md:
YAML frontmatter (required):
name: kebab-case, max 64 chars, must match directory namedescription: max 1024 chars, no<or>characters
Optional frontmatter:
license,compatibility,metadata,allowed-tools
Markdown body: Instructions loaded on trigger. Keep under 500 lines.
Bundled resources (optional subdirectories):
references/— loaded as needed (detailed tables, examples)scripts/— executed, not loaded into contextassets/— used in output (templates, images)
Harbor Documentation Map
| Resource | Location |
|---|---|
| Harbor repo | https://github.com/harbor-framework/harbor |
| Harbor docs | https://harborframework.com/docs |
| Harbor cookbook | https://github.com/harbor-framework/harbor-cookbook |
| Task config model | src/harbor/models/task/config.py |
| Verifier | src/harbor/verifier/verifier.py |
| CLI entry points | src/harbor/cli/ |
| Agent base class | src/harbor/agents/base.py |
| Adapter system | src/harbor/adapters/ |
Conventions
- Each skill directory has a
SKILL.md(required) plus optionalreferences/subdirectory - Keep
SKILL.mdbody < 500 lines; put detailed tables and walkthroughs inreferences/ - Descriptions should be slightly "pushy" — err toward triggering rather than not
- No
scripts/— Harbor already has CLI tools for scaffolding and validation (harbor tasks init,harbor adapters init) - The repo supports Claude Code (
.claude-plugin/), Codex, and Cursor (.cursor-plugin/); keep both plugin configs in sync when adding or renaming skills - The
namefrontmatter field must match the directory name exactly
Common Pitfalls
- Don't exceed 1024 chars in the
descriptionfrontmatter field - Don't use
<or>in the description field (breaks YAML parsing) - Don't duplicate content between
SKILL.mdbody andreferences/— body should point to references - Don't write skills that wrap simple CLI commands — skills should teach complex multi-step workflows
- Don't put Harbor version-specific details in skills without noting the version
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 · 58 lines · 651 tokens per session scan A 6367592b7874
skills AGENTS.md is an instructions file published in the GitHub repository harbor-framework/skills (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 651 tokens to every session, about $0.0033 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
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.
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.
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).
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.
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).
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.