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 agentmods add skills/cinqueizumi/softcover/releasenpx skills add CinqueIzumi/Softcover --skill releasegit clone --depth 1 https://github.com/CinqueIzumi/SoftcoverWrote 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/cinqueizumi/softcover/release)<a href="https://agentmods.dev/skills/cinqueizumi/softcover/release"><img src="https://agentmods.dev/badge/skills/cinqueizumi/softcover/release.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.00820 |
| Opus 5 | $0.00027 | $0.00410 |
| Sonnet 5 | $0.00011 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
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 4d 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.
What it actually says
Orchestrate a release-prep pass by composing the existing skills. Never commit or tag; leave all changes unstaged for the user to review.
Steps:
-
Invoke the
update-readmeskill via the Skill tool to bring the README current with the latest features. -
Invoke the
style-checkskill via the Skill tool to auto-fix style and run the full gate. If the gate is not green, stop and report — do not bump the version on a red build. -
Read the current
versionCodeandversionNamefromapp/build.gradle.ktsand show them to the user. Ask for the newversionName(suggest the next semantic version). If the user provided one as an argument, use that. -
Invoke the
set-version-nameskill via the Skill tool with the new version name. It sets the version name across all platforms (AndroidversionName, iOSMARKETING_VERSION, desktoppackageVersion) and bumps the build number together — do not edit any of those fields yourself. -
Close the shipped milestone. If a GitHub milestone matches the version being released, ask the user to confirm, then close it (
gh api -X PATCH repos/{owner}/{repo}/milestones/{n} -f state=closed). This is the one live GitHub write in an otherwise local skill, so confirm first; it is trivially reversible by reopening.Why it belongs here: the public roadmap is built from open milestones, so leaving it open makes
ROADMAP.mdname the new version as the current release and list it as a future release in the same file. Skipping this ships a self-contradictory roadmap to the in-app Roadmap screen. -
Update the "what shipped" sentence in
scripts/roadmap/header.md. This is the only line in the public roadmap that no machine can derive, and release time is the only moment it can be written.- Read the commits since the previous tag (
git log --no-merges --format=%s $(git describe --tags --abbrev=0)..HEAD) and summarise the release in the public, editorial voice already used in that file — what a reader gets, not what changed internally. - Lead with the new version and prune older detail rather than letting the sentence accumulate every patch forever. One or two sentences total.
- Leave
{{CURRENT_VERSION}}alone — it is substituted from Gradle at generation time.
- Read the commits since the previous tag (
-
Regenerate the public roadmap:
python3 scripts/roadmap/generate_roadmap.py --write.This is mandatory, not optional.
ROADMAP.mdis a generated file, and the Roadmap workflow runs--checkon any pull request touchingROADMAP.mdorscripts/roadmap/**. Editingheader.mdin step 6 without regenerating leaves the file stale and fails CI on the release PR. Verify with--checkbefore reporting. -
Report a consolidated summary: README changes, the check result, the version transition (e.g.
versionName / MARKETING_VERSION / packageVersion: 2.4.0 → 2.5.0, versionCode / CURRENT_PROJECT_VERSION: 29 → 30), which milestone was closed, and the new "what shipped" sentence.
Do not create a commit or tag. Do not write Google Play release notes. Never hand-edit
ROADMAP.md — it is generated; change header.md or a milestone description and regenerate.
Leave all changes unstaged in the working tree.
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.
- 4d ago First seen · 33 lines · 54 tokens per session scan A 4dfead892b16
release is a skill published in the GitHub repository CinqueIzumi/Softcover (11 stars, last pushed 4d ago), licensed MIT. It adds 54 tokens to every session and 820 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 2026-08-30.
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.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…