av/harbor is a command-line tool and companion app that uses Docker Compose to start a connected local stack of language-model backends, user interfaces, and supporting AI services. People use it to run services such as Ollama, llama.cpp, vLLM, Open WebUI, search, voice, and image-generation tools without configuring their connections manually, while the catalogue provides agent workflows for operating Harbor.
Borrowing it
Nothing to install: this file belongs to av/harbor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/av/harbor/main/.agents/skills/facts-implement/SKILL.mdgit clone --depth 1 https://github.com/av/harborWrote 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/skills/av/harbor/facts-implement)<a href="https://agentmods.dev/skills/av/harbor/facts-implement"><img src="https://agentmods.dev/badge/skills/av/harbor/facts-implement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/av/harbor/facts-implement"><img src="https://agentmods.dev/badge/skills/av/harbor/facts-implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00048 | $0.01623 |
| Opus 5.5 | $0.00019 | $0.00649 |
| Sonnet 5.5 | $0.00010 | $0.00325 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
facts-implement 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 2mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
facts-implement
You are a fact-driven implementer. Your job is to take @spec facts and implement them in code — systematically, in a single session. This is the @spec → @implemented lifecycle transition.
Tip: Short CLI aliases are available and recommended for high-frequency operations: ll (list --light), at <id> <tag> (quick --add-tag), rt <id> <tag> (quick --remove-tag), rm, and ls. All extra arguments are forwarded. See facts --help or facts skills show facts.
Goal
Each @spec fact is a precise, actionable requirement. Implement all @spec facts, using subagents to parallelize independent work where possible. Mark completed facts by transitioning them from @spec to @implemented. If you cannot complete all facts, report exactly what remains and why.
Important: Only implement @spec facts. @draft facts are not yet refined — they need the facts-refine skill first. Untagged facts are already true. If you see facts without lifecycle tags that aren't implemented, classify them or suggest running facts-discover first.
Process
1. Load the full spec
Run facts list to see the entire specification. Read and understand all facts — you need the full picture to make good ordering and grouping decisions, even though you will only implement unimplemented facts.
Read the ## domain section first if it exists (it lives in the main .facts file) — it establishes the project's vocabulary. Use these entity names when reasoning about implementation order and dependencies between facts.
2. Identify remaining work
Run facts check to see which command-facts pass and which fail. This also validates the fact sheet structure (lint errors abort check early).
Run facts list --tags "spec" to see facts ready to implement. This is your implementation target.
Cross-reference: a @spec fact may already pass its validation command. If facts check shows it passing, verify the implementation is complete and transition it — do not re-implement.
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.
- 2mo ago First seen · 140 lines · 48 tokens per session scan A f320c1e1d66f
facts-implement is a skill published in the GitHub repository av/harbor (3,263 stars, last pushed 6d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,623 once invoked, about $0.0002 per session on Opus 5.5. 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.
facts-implement compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| facts-implementav/harbor | Skill | 3.3k | 6d ago | Apache-2.0 | A | 48 | Claude Code, Codex |
| hugging-face-tool-buildersynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 67 | Claude Code, Codex |
| agent-builderchandrudp29/skillhub | Skill | 14 | 4mo ago | MIT | A | 42 | Claude Code, Codex |
| synapsedinglebear-ai/synapse | Skill | 2 | 4d ago | AGPL-3.0 | A | 67 | Claude Code |
| docker-essentialsasgarovf/locusai | Skill | 23 | 8mo ago | MIT | A | 35 | Claude Code |
| docker-managementfurkangonel/cowrangler | Skill | 1 | 1mo ago | MIT | C | 16 | Claude Code, Codex |
| clinicaltrials-databasesynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 47 | Claude Code, Codex |