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 richkuo/rk-skills --skill sync-docs-releasegit clone --depth 1 https://github.com/richkuo/rk-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/richkuo/rk-skills/sync-docs-release)<a href="https://agentmods.dev/skills/richkuo/rk-skills/sync-docs-release"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/sync-docs-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/richkuo/rk-skills/sync-docs-release"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/sync-docs-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 57 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00076 | $0.00783 |
| Opus 5.5 | $0.00030 | $0.00313 |
| Sonnet 5.5 | $0.00015 | $0.00157 |
| Haiku 4.5 | $0.00008 | $0.00078 |
Grade A, and why
sync-docs-release 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 21d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sync-docs-release
Runs three operations in strict sequence, all in the main session. Do not skip steps or reorder them, and do not delegate any step to a subagent.
Step 1 — Sync docs
Invoke the sync-docs skill via the Skill tool and follow it to completion here, passing the user's request plus any session context (target branch, last-sync SHA, specific files).
sync-docs works in its own worktree off the latest origin/<default> and ends with either "no doc changes" or an open docs PR. Summarize the doc edits and the PR for the user before proceeding.
Step 2 — Decide how the docs PR relates to the release
If sync-docs reported no doc changes, go straight to Step 3.
When the caller's approved plan already authorizes the docs-sync PR and its merge (as the milestone-workflow close-out does with merging on), take the merge-then-release choice below without asking. Otherwise ask the user once (AskUserQuestion) how Step 3 should relate to it:
- Merge the doc PR once its checks pass, then release from the updated default branch (recommend this one).
- Release now without the doc changes, leaving the PR open.
- Stop here with no release.
Treat their answer, or the caller's plan, as authorization for that one merge only. Their answer never authorizes the version-bump PR merge that create-release asks about. Never merge without that answer or that plan, and never merge past a failing or pending check.
Step 3 — Create a release
Skip this step entirely if the user chose "stop here".
If they chose merge-then-release, first wait for the PR's checks (gh pr checks <n> --watch); a failing or pending check stops the run with the PR left open and no release. Apply the create-release step 4 Merge bullet's rules to this docs PR: its no-checks rule (no checks reported counts as no failing check only when $DEFAULT requires no status check) and its merge-method choice (--squash, else --merge, else --rebase, as the repo allows). Then merge it with that method and its head pinned (--match-head-commit <head-sha>). After the merge command, read gh pr view <n> --json state,mergeCommit. When state is not MERGED (a merge queue holds the PR, or gh pr merge only enabled auto-merge), stop with the PR left open, report its state, and start no release. Otherwise git fetch origin and confirm git merge-base --is-ancestor <mergeCommit.oid> "origin/$DEFAULT" holds before create-release starts. On both release paths, remove the sync-docs worktree (git worktree remove <path>; the branch and the PR stay) and run git fetch origin before create-release starts. Do not check out or pull the local default branch.
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.
- 21d ago Changed facf6e972eb7
- 28d ago Changed · -31 lines · -3 tokens per session 44237d218371
- 1mo ago First seen · 68 lines · 79 tokens per session scan A cdcc0f69c3c4
sync-docs-release is a skill published in the GitHub repository richkuo/rk-skills (50 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 783 once invoked, about $0.0003 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.
Other skills, from other repositories
branch-finish
You MUST use this when verified development work is ready for an integration or handoff decision - merging, pushing, opening a pull request, preserving or discarding a branch, or cleaning up its workspace. Covers safe completion choices based on the actual Git state and verification evidence.
github-release
Guides IA through releasing a new version of a GitHub library end-to-end. Handles SemVer versioning and Keep a Changelog formatting automatically.
create-github-pull-request-from-specification
Create GitHub Pull Request for feature request from specification file using pullrequesttemplate.md template.
shipping
Project shipping is authorized immediate delivery execution for identified, already-completed software work. Select only when the user explicitly authorizes an immediate concrete action to commit, push, prepare or create a PR, merge, tag, package, publish, release, deploy, perform an exact repository handoff, or…
antigravity-maintainer-batch-release
Run protected AAS maintainer sweeps, PR merge batches, resumable review, immutable distribution, Core checks, and scripted releases. Use for repository maintenance, main alignment, CLI/MCP/Workbench c.
gh-cli
GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.