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/erraggy/oastools/publish-releasenpx skills add erraggy/oastools --skill publish-releasegit clone --depth 1 https://github.com/erraggy/oastoolsWrote 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/erraggy/oastools/publish-release)<a href="https://agentmods.dev/skills/erraggy/oastools/publish-release"><img src="https://agentmods.dev/badge/skills/erraggy/oastools/publish-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 5.1 | $0.00033 | $0.00632 |
| Opus 5 | $0.00016 | $0.00316 |
| Sonnet 5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
publish-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 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.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
publish-release
Publish a prepared release to GitHub. This is phase 7 of the release process.
Usage: /publish-release <version> (e.g., /publish-release v1.46.0)
Prerequisites
Before running this skill:
- Run
/prepare-release <version>to complete phases 1-6 - Verify prepared notes exist at
.release/notes-<version>.md - Review the release notes in that file
- Ensure you're ready to publish (this is irreversible)
Process
⚠️ CRITICAL: This skill wraps
publish-release.sh. Do NOT run release commands manually.
Step 1: Validate Version Argument
If no version is provided, stop and ask the user:
Error: Version argument required.
Usage: /publish-release <version>
Example: /publish-release v1.46.0
If the version doesn't match the vX.Y.Z pattern, reject it:
Error: Version must match vX.Y.Z pattern (e.g., v1.46.0)
Got: <invalid-version>
Step 2: Confirm with User
Use the AskUserQuestion tool to confirm before proceeding:
Ready to publish release **<version>**?
This will:
1. Create and push git tag <version>
2. Trigger goreleaser workflow
3. Wait for draft release with binaries
4. Publish the release (irreversible)
Proceed? [Yes / Cancel]
Step 3: Run the Publish Script
From the repository root, run:
.claude/scripts/publish-release.sh <version>
The script handles:
- Verifies on main branch
- Creates and pushes annotated tag
- Waits for goreleaser workflow
- Verifies draft has 8 assets (binaries + checksums)
- Reads prepared notes from
.release/notes-<version>.md(fails if missing) - Publishes with
gh release edit --draft=false - Verifies published release
Step 4: Report Results
On success, report:
✅ Release <version> published successfully!
View release: https://github.com/erraggy/oastools/releases/tag/<version>
The release includes:
- 8 binary assets for all platforms
- Enhanced release notes (from prepare step)
- Homebrew formula will update automatically
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 · 99 lines · 33 tokens per session scan A 2d9568596bff
publish-release is a skill published in the GitHub repository erraggy/oastools (5 stars, last pushed 7d ago), licensed MIT. It adds 33 tokens to every session and 632 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
lathe-release
Run Lathe release validation and publishing workflows. Use when the user asks to prepare, validate, cut, tag, publish, or ship a Lathe versioned release; runs the captured pre-release regression gate before tagging.
openapi-glossary
Use consistent OpenAPI terminology and definitions when writing documentation, educational material, and tooling guidance.
scalar-docs
Skill for writing and updating scalar.config.json — Scalar Docs configuration reference for users and LLMs.
scalar-design-system
Scalar's design system — design tokens, theming (@scalar/themes), CSS variables, and the @scalar/components library. Use when designing or implementing Scalar UI, especially with Paper (code-to-design / design-to-code), so output matches real Scalar tokens, colors, typography, spacing, and components instead of…
cloud-agents-starter
Minimal starter runbook for cloud agents to install dependencies, run packages, execute tests, and troubleshoot the Scalar monorepo quickly.
mock-server
Build, customize, and troubleshoot OpenAPI mock servers with @scalar/mock-server, including x-handler, x-seed, authentication, and Docker.