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 Starfie1d1272/dsh-github-skills --skill gh-publishgit clone --depth 1 https://github.com/Starfie1d1272/dsh-github-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/starfie1d1272/dsh-github-skills/gh-publish)<a href="https://agentmods.dev/skills/starfie1d1272/dsh-github-skills/gh-publish"><img src="https://agentmods.dev/badge/skills/starfie1d1272/dsh-github-skills/gh-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/starfie1d1272/dsh-github-skills/gh-publish"><img src="https://agentmods.dev/badge/skills/starfie1d1272/dsh-github-skills/gh-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00047 | $0.00627 |
| Opus 5 | $0.00023 | $0.00313 |
| Sonnet 5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
gh-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 12d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Publish
Remote publication is this skill's primary purpose, so the user's requested publish scope defines which remote steps are authorized: push task-scoped changes and, when requested, open a pull request. Pushing does not imply opening a PR. Fork-based external contributions follow the same flow from a checkout of the target repository lineage.
Branching and committing are internal steps here, not entry points: use this skill when the user wants changes pushed or a PR opened.
Workflow
- Resolve target checkout. Same repository → the relevant existing checkout. External contribution → create or reuse the user's fork, and work from a checkout/worktree that belongs to the target repository lineage — never continue from an unrelated checkout. Ambiguous target, fork, or base → stop and report.
- Confirm scope. Inspect the actual status and diff; use
scripts/publish-preflight.mjswhen useful. Stage only task-owned changes. Mixed task/unrelated hunks → stage selectively. If scope cannot be separated reliably, stop before publishing. - Branch. Keep a suitable existing feature branch, or create a task branch from the intended base following the repository's convention.
- Commit. Confirmed scope only; concise message derived from the actual diff and task intent. Do not bypass hooks.
- Verify. Run only the relevant existing checks for the touched area.
- Push. Push to the appropriate tracked or fork remote; never assume
origin. No force push unless explicitly requested, with the risk stated. If the user's requested publish scope ends at push, verify the pushed branch, report the result, and stop — do not open a PR. - Open PR, when requested. Check for an existing PR first. Use
correct target/base/head and fork semantics. Draft is the default
unless the user explicitly wants ready-for-review. Prefer a suitable
visible PR-create capability;
ghfallback. Body from the actual diff, template, and validation. - Verify published result. Verify the remote branch after push. When a PR was opened or updated, also re-read it and verify target/base/head, changed-file scope, and available checks. If the published state differs from the intended scope, report it — do not declare success.
- Report. Branch, commit, PR (when applicable), validation/check state, and any uncertainty.
What ships with it
1 file 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.
- 12d ago First seen · 56 lines · 47 tokens per session scan A 9aadb0ed958d
gh-publish is a skill published in the GitHub repository Starfie1d1272/dsh-github-skills (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 47 tokens to every session and 627 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
github-publish-changes
Publish intentional local changes by confirming scope, creating a branch when needed, staging selected files, committing, pushing, and creating a Draft Pull Request through the connected GitHub service.
dsh-git-commit
A Git commit guide for writing standardised commit messages and performing basic checks before committing code. Git commits are saved checkpoints in a project’s history.
market-pre-push-checks
Use before pushing, merging, or claiming a green tree in dsh-agent-plugins-market, to select the smallest checks that cover the outgoing diff instead of reflexively running the full suite.
code-review-zh
A Git-based code review workflow that compares changes from a chosen commit, branch, tag, or merge point. It checks both whether the code follows the repository's written standards and whether it implements the requested specification.
git-workflow
Git workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices for teams of all sizes. Use when choosing a branching strategy, writing commit conventions, deciding merge versus rebase, or resolving conflicts.
commit
Use when starting implementation work on a task, or when the user asks you to commit changes to the repository.