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/goldziher/spikard/release-workflownpx skills add Goldziher/spikard --skill release-workflowgit clone --depth 1 https://github.com/Goldziher/spikardWrote 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/goldziher/spikard/release-workflow)<a href="https://agentmods.dev/skills/goldziher/spikard/release-workflow"><img src="https://agentmods.dev/badge/skills/goldziher/spikard/release-workflow.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 5.1 | $0.00077 | $0.01000 |
| Opus 5 | $0.00039 | $0.00500 |
| Sonnet 5 | $0.00015 | $0.00200 |
| Haiku 4.5 | $0.00008 | $0.00100 |
Grade C, and why
release-workflow 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 5d 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.
task clean # cargo clean + alef clean + rm -rf dist/ .alef/ caches How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spikard Release Workflow
Ground truth: spikard is a Rust workspace (core library + spikard-cli +
polyglot bindings). It has no set-version task — the equivalent is
task version:set (a version-sync include). Cargo.toml is the single source
of truth; version:set syncs it to every binding manifest.
1. Set the version
task version:set -- X.Y.Z # e.g. task version:set -- 0.7.0-rc.1
version:set takes the version as a -- positional argument (CLI_ARGS). It runs
alef sync-versions --set <version> then the full sync (regenerate READMEs,
docs, bindings, scaffold, stubs, e2e, and precise cargo update for the core
crate across dependent manifests). Bump variants also exist:
task version:bump:patch, task version:bump:minor, task version:bump:major.
task version:show prints the current version.
Verify:
task version:show
grep -m1 '^version' Cargo.toml
2. Update the CHANGELOG
Move every [Unreleased] bullet in CHANGELOG.md into a new
## [X.Y.Z] - YYYY-MM-DD section (grouped Added / Changed / Fixed / Removed).
Re-create an empty [Unreleased]. Never tag an empty section.
3. Clean-tree precondition (hard gate)
Never release a dirty or failing tree.
poly fmt --check . # formatting clean (task format:check)
poly lint . # lint clean (task lint)
task test # Rust core tests pass (rust:test)
Use poly fmt --fix . (or task format) to apply formatting, then re-stage.
For a full cross-binding gate before a release, run task test:all
(task test + alef test). Optionally validate manifests with
task publish:validate (alef publish validate). Fix any failure — do not
release past it.
4. Commit, tag, and publish the GitHub release
git add -A
git commit -m "chore(release): X.Y.Z"
git tag -a vX.Y.Z -m "vX.Y.Z"
git push origin main
git push origin vX.Y.Z
gh release create vX.Y.Z --title "vX.Y.Z" --generate-notes
Add --prerelease for RC/beta tags. Use --notes-file from the new CHANGELOG
section instead of --generate-notes when the changelog entry is richer. A bare
git tag is not a release — always run gh release create. Tag-based releases
trigger the multi-platform / multi-registry publish workflows.
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.
- 5d ago First seen · 104 lines · 77 tokens per session scan C dd0dc15b047c
release-workflow is a skill published in the GitHub repository Goldziher/spikard (119 stars, last pushed 23d ago), licensed MIT. It adds 77 tokens to every session and 1,000 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 2026-08-30.
Other skills, from other repositories
backport-pr
Backport a merged Next.js pull request from canary to a previous release branch such as next-16-2. Use when the user asks to backport, cherry-pick, or open a backport PR from a PR number to an older Next.js version. Covers finding the merged PR commit, creating a backport branch from the target release branch…
version-release
Choose and apply the correct semantic version bump for this repository. Use for every user-visible release, before merge when a change set should ship as patch, minor, or major, and whenever package/plugin/desktop version metadata must stay synchronized.
release-guard
Run release-readiness checks for this repository. Use when validating docs, scripts, verification coverage, and operational safety before merge or release.
noodle-release
Prepare a versioned Noodle release by updating package.json, inspecting changes since the latest tag, auditing every repository-maintained skill, synchronizing affected README, AGENTS.md, tests, CHANGELOG.md, noodle-site documentation, and a release blog post, then running the release validation. Use for release…
npm-publish
Use when publishing Node/npm packages from a repository or monorepo, especially scoped public packages, beta/latest dist-tags, workspace publishing, npm 2FA, publish verification, local tarball smoke tests, and debugging npm publish/install errors such as E403, E404, ENOVERSIONS, ELOOP, or pack destination failures.
pull-request
Use this whenever the user asks to "open a PR", "ship this", "create the pull request", "make a PR", or once a feature/fix is verified and ready to push. Full lifecycle: branch → commit (commitizen) → issue → draft PR → CI → ready → autonomous monitor loop (fix comments, resolve threads, iterate until CI green + zero…