agent-skills-repo-publishing

agent-skills-repo-publishing is a skill for Claude Code, Codex from davidtoby/agent-skills. It costs 74 tokens per session (1,361 once invoked), scanned C, original, MIT.

A workflow for adding, updating, packaging, and publishing reusable coding-agent skills in a GitHub repository. GitHub is a service for storing and collaborating on code, while a package is a prepared distributable copy of a skill.

In plain words
What is it for?
It is for maintaining skill files, rebuilding affected packages, validating the repository, copying skills into a local installation, and pushing changes to GitHub.
Why use it?
It removes repeated manual work around indexes, validation, package rebuilding, local syncing, and repository updates.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/rebuild_all_packages.py --skill <skill-name>.

Good fit It is for maintaining skill files, rebuilding affected packages, validating the repository, copying skills into a local installation, and pushing changes to GitHub.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/davidtoby/agent-skills
agentmods
npx agentmods add skills/davidtoby/agent-skills/agent-skills-repo-publishing

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agent-skills-repo-publishing

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidtoby/agent-skills/agent-skills-repo-publishing/github.svg)](https://agentmods.dev/skills/davidtoby/agent-skills/agent-skills-repo-publishing)
Your own site
<a href="https://agentmods.dev/skills/davidtoby/agent-skills/agent-skills-repo-publishing"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/agent-skills-repo-publishing/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.

agentmods 80×15 button for agent-skills-repo-publishing

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidtoby/agent-skills/agent-skills-repo-publishing"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/agent-skills-repo-publishing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,361 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.01361
Opus 5 $0.00037 $0.00681
Sonnet 5 $0.00015 $0.00272
Haiku 4.5 $0.00007 $0.00136

Measured 8d ago against content hash 743e8a8e4a14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

agent-skills-repo-publishing scanned grade C 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 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf skills/<skill-name>/scripts/__pycache__
skills/.archive/umbrella-curation-2026-04-29/user-imports/agent-skills-repo-publishing/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Skills Repo Publishing

Publish battle-tested skills to davidtoby/agent-skills in a way that keeps the repo valid and the local Hermes copy in sync.

Quick start

  1. Work in the local clone at ~/.Hermes/workspace/output/skill_repo_cache/agent-skills.
  2. Add or edit the skill under skills/<skill-name>/.
  3. Update repo indexes (README.md, skills/README.md) so the new skill is discoverable.
  4. Rebuild affected .skill packages with scripts/rebuild_all_packages.py --skill ....
  5. If validation fails because another package is stale, rebuild that package too.
  6. Copy the final skill folder into local Hermes skills under ~/.hermes/skills/user-imports/.
  7. Commit, fetch/rebase, and push via SSH to [email protected]:davidtoby/agent-skills.git.
  8. Verify the pushed commit on GitHub.

Repo-specific workflow

Working repo

Use:

~/.Hermes/workspace/output/skill_repo_cache/agent-skills

This repo contains:

  • skills/ source-of-truth folders
  • packages/*.skill packaged artifacts
  • scripts/rebuild_all_packages.py
  • scripts/validate_skills_repo.py

Add or update a skill

Required files:

  • skills/<name>/SKILL.md
  • optional references/, scripts/, assets/

Important repo-specific mapping:

  • the GitHub skills repo uses a flat skills/<name>/ layout
  • local Hermes may store the same skill under namespaced paths such as ~/.Hermes/skills/user-imports/<name>/ or ~/.Hermes/skills/openclaw-imports/<name>/
  • when publishing an update that was made locally first, sync the local skill folder into the repo path explicitly rather than assuming the repo mirrors the local namespace structure

Typical sync pattern:

rsync -a --delete ~/.Hermes/skills/user-imports/<name>/ \
  ~/.Hermes/workspace/output/skill_repo_cache/agent-skills/skills/<name>/

# or, for an OpenClaw-imported skill
rsync -a --delete ~/.Hermes/skills/openclaw-imports/<name>/ \
  ~/.Hermes/workspace/output/skill_repo_cache/agent-skills/skills/<name>/

Read the full file on GitHub · 161 lines

Changes

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.

  1. 8d ago First seen · 161 lines · 74 tokens per session scan C 743e8a8e4a14

Subscribe to this mod's changes

agent-skills-repo-publishing is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 1,361 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories