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/release/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/release)<a href="https://agentmods.dev/skills/av/harbor/release"><img src="https://agentmods.dev/badge/skills/av/harbor/release/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/release"><img src="https://agentmods.dev/badge/skills/av/harbor/release.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 | $0.00098 | $0.01847 |
| Opus 5.5 | $0.00039 | $0.00739 |
| Sonnet 5.5 | $0.00020 | $0.00369 |
| Haiku 4.5 | $0.00010 | $0.00185 |
Grade A, and why
release scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.parse How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harbor Release Procedure
Releasing Harbor is a sequential pipeline: bump the version constant, run codegen (which propagates the version across the monorepo and syncs docs to the wiki), research what changed, update the README News section, run the same local lint gate used by CI, commit, push, and open a pre-filled GitHub release form.
Pre-flight
Before starting, verify two things:
- Clean working tree —
git statusshould show no uncommitted changes. The codegen step touches many files; starting dirty makes the release commit noisy. - Wiki repo exists —
release.shpushes docs to../harbor.wiki. If the directory doesn't exist, the docs push will fail. Clone it first if missing:git clone https://github.com/av/harbor.wiki.git ../harbor.wiki
Step 1 — Bump Version
Open .scripts/seed.ts and change the VERSION constant (line ~9):
const VERSION = "X.Y.Z";
Bump patch by default (e.g. 0.4.2 → 0.4.3). Bump minor or major only
when the user explicitly asks.
This constant is the single source of truth — the seed script propagates it to
pyproject.toml, package.json, harbor.sh, app/package.json,
app/src-tauri/tauri.conf.json, app/src-tauri/Cargo.toml, and
services/boost/pyproject.toml.
Step 2 — Run Codegen
bash .scripts/release.sh
Note: harbor dev only runs .scripts/*.ts Deno scripts, so release.sh must
be invoked directly with bash. The script:
- Seeds the version into all targets (
harbor dev seed,seed-cdi,seed-traefik) - Runs the human lint pass (
harbor dev lint) - Refreshes
app/src-tauri/Cargo.lockto match the bumpedCargo.toml(cargo update --workspace); ifcargois missing it warns — sync the lock manually before committing - Regenerates docs and pushes them to the wiki repo (
../harbor.wiki)
Wait for it to complete. Check the output for errors — especially the wiki push,
which can fail if there are merge conflicts in ../harbor.wiki.
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 · 212 lines · 98 tokens per session scan A 659b39e0d2d5
release is a skill published in the GitHub repository av/harbor (3,263 stars, last pushed 6d ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,847 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| releaseav/harbor | Skill | 3.3k | 6d ago | Apache-2.0 | A | 98 | Claude Code, Codex |
| githubbug-ops/zeph | Skill | 66 | 3d ago | MIT | A | 104 | Claude Code, Codex |
| gitbug-ops/zeph | Skill | 66 | 3d ago | MIT | A | 106 | Claude Code, Codex |
| pypi-releasealchemiststudiosDOTai/tunacode | Skill | 125 | 1mo ago | MIT | A | 52 | Claude Code, Codex |
| shipepicsagas/epic-harness | Skill | 20 | yesterday | Apache-2.0 | A | 37 | Claude Code |
| changelog-generatorskrun-dev/skrun | Skill | 209 | 1mo ago | MIT | A | 68 | Claude Code, Codex |
| synthetic-release-notestheinfosecguy/razin | Skill | 16 | 13d ago | MIT | A | 15 | Claude Code, Codex |