slidespeak-onbrand: Skill for Claude Code

.agents/skills/release/SKILL.md

release is a skill for Claude Code from SlideSpeak/slidespeak-onbrand. It costs 39 tokens per session (1,057 once invoked), scanned A, original, MIT.

A procedure for releasing this repository's changes through Git branches and GitHub pull requests. It includes preparing the automated release change, promoting it from develop to main, and preserving the intended merge history.

In plain words
What is it for?
It helps find and merge the release pull request, open and merge the promotion pull request, verify checks, and handle release-related fixes.
Why use it?
It reduces the chance of skipping a release step or merging changes before required automated checks pass. It also defines what to do when checks fail.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is SlideSpeak/slidespeak-onbrand's own configuration. It tells Claude Code how to work on slidespeak-onbrand itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything slidespeak-onbrand configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SlideSpeak/slidespeak-onbrand. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SlideSpeak/slidespeak-onbrand/develop/.agents/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SlideSpeak/slidespeak-onbrand

Made for: Claude Code.

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 release

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

agentmods 80×15 button for release

Your own site · 80×15
<a href="https://agentmods.dev/skills/slidespeak/slidespeak-onbrand/release"><img src="https://agentmods.dev/badge/skills/slidespeak/slidespeak-onbrand/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,057 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00039 $0.01057
Opus 5 $0.00019 $0.00528
Sonnet 5 $0.00008 $0.00211
Haiku 4.5 $0.00004 $0.00106

Measured 9d ago against content hash efdd723fd62d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 9d 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.

.agents/skills/release/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

Run the full release path for this repository:

  1. Find and merge the Release Please PR into develop.
  2. Open or update the promotion PR from develop to main.
  3. Merge the promotion PR into main with a merge commit.

Do the whole release. Do not stop after opening PRs unless the user explicitly asks for a pause or a required approval is missing.

Preconditions

  • Work from a clean tree. If local changes exist, inspect them and avoid overwriting user work.
  • Use gh for GitHub operations and git for local branch state.
  • Treat CI status as authoritative. Before merging each PR, verify all required checks are passing.
  • If a check fails, investigate, fix the repository, push the fix, and wait for CI again.
  • Preserve release history:
    • Release Please PR into develop: squash merge.
    • Promotion PR from develop to main: merge commit.

Find the Release Please PR

Look for an open PR created by the Release Please bot against develop. It is usually titled like chore: release ..., chore(...): release ..., or similar.

gh pr list \
  --state open \
  --base develop \
  --json number,title,author,headRefName,baseRefName,url,labels,statusCheckRollup,mergeStateStatus \
  --jq '.[] | select((.author.login | test("release-please|github-actions|app/release-please"; "i")) or (.title | test("^chore(\\(.+\\))?: release"; "i")) or ([.labels[].name] | index("release-please")))'

If multiple candidates exist, inspect each one and pick the active Release Please PR that updates version files, changelogs, or release manifests. If none exists, report that there is no pending release PR and stop.

Verify and Fix CI

For each PR before merging:

gh pr view {number-or-url} --json number,title,url,headRefName,baseRefName,mergeStateStatus,statusCheckRollup
gh pr checks {number-or-url} --watch

If checks are failing:

  • Read failing logs with gh run view / gh run watch / gh run download as needed.
  • Reproduce locally where practical with the matching package script from package.json.
  • Fix the actual issue in the repo, commit or amend on the relevant PR branch, push, and wait for CI again.
  • Do not merge with failing or pending required checks.

Read the full file on GitHub · 128 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. 9d ago First seen · 128 lines · 39 tokens per session scan A efdd723fd62d

Subscribe to this mod's changes

release is a skill published in the GitHub repository SlideSpeak/slidespeak-onbrand (7 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,057 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.