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 skills add glebis/claude-skills --skill repo-publishgit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/repo-publish)<a href="https://agentmods.dev/skills/glebis/claude-skills/repo-publish"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/repo-publish/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/glebis/claude-skills/repo-publish"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/repo-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 91 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 127 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00062 | $0.01402 |
| Opus 5 | $0.00031 | $0.00701 |
| Sonnet 5 | $0.00012 | $0.00280 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
repo-publish 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 8d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Publish
End-to-end pipeline for taking a project from "I made changes" to "live on a remote". Runs quality gates, generates an intelligent multi-commit history, pushes, and verifies the deploy.
When to Use
Use this skill when:
- The user says "publish", "release", "ship it", "push to remote", "deploy this"
- A project has accumulated local changes that need to land cleanly
- A version bump or release needs to be cut
- The user explicitly asks to run the full landing-the-plane workflow
Do not use this skill for:
- Single quick commits the user is doing themselves
- Documentation-only edits (use the project's own docs workflow)
- Anything involving secrets/credentials (the scripts will skip those files)
Workflow Decision Tree
Start here. Pick the lane based on the user's intent:
User wants to publish
├─ Has local changes? ──── no ──► Just push / bump version
├─ Want a release? ──── yes ──► [Release mode](#release-mode)
└─ Just routine commit? ──────► [Push mode](#push-mode)
Push Mode
For ordinary commits that need to land.
Step 1 — File remaining work
Run the issue tracker step:
bd ready # What's pending
bd show <id> # Inspect any blockers
bd update <id> --status in_progress # Claim work
If you can't bd, ask the user how they track issues for this project. Don't silently skip it — issue hygiene is part of the gate.
Step 2 — Run quality gates
Inspect package.json, pyproject.toml, Makefile, or whatever exists and run whatever the project defines as "test + lint + build":
# Node
npm test && npm run lint && npm run build
# Python
pytest && ruff check . && mypy .
# Go
go test ./... && go vet ./...
# Rust
cargo test && cargo clippy -- -D warnings
# Makefile-driven
make test lint build
If a gate fails, stop. Report which gate failed and the relevant error. Don't try to fix the code in the same publish flow — open a fix-PR first.
For projects without an obvious test command, run ls to find the closest script and ask the user.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 158 lines · 62 tokens per session scan A b550f6ce54c6
repo-publish is a skill published in the GitHub repository glebis/claude-skills (375 stars, last pushed 10d ago), licensed MIT. It adds 62 tokens to every session and 1,402 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.