agentmods.dev

reef: Skill for Claude Code

.agents/skills/releasing-reef/SKILL.md

releasing-reef is a skill for Claude Code, Codex from Blushyes/reef. It costs 162 tokens per session (3,007 once invoked), scanned A, original, Apache-2.0.

A release guide for the Reef project, whose releases are triggered by pushing version tags such as v1.2.3 to GitHub. It describes version updates, tags, automated builds, package publishing, and release notes.

In plain words
What is it for?
Use it to bump the version, commit changes, push a release tag, check supported build targets, and format GitHub Release notes.
Why use it?
It clarifies the required release sequence and prevents manual publishing steps that the project’s automation already handles.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Blushyes/reef's own configuration. It tells Claude Code and Codex how to work on reef 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 reef configures →

not rated 81repo +1 15d ago A scan SkillSpector: pass 162 tokens original Apache-2.0
View source ↗ Blushyes/reef blushyes.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to Blushyes/reef. 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/Blushyes/reef/main/.agents/skills/releasing-reef/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Blushyes/reef

Made for: Claude Code, Codex.

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 releasing-reef

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/blushyes/reef/releasing-reef"><img src="https://agentmods.dev/badge/skills/blushyes/reef/releasing-reef.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,007 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00162 $0.03007
Opus 5 $0.00081 $0.01503
Sonnet 5 $0.00032 $0.00601
Haiku 4.5 $0.00016 $0.00301

Measured 10d ago against content hash dad84d0c9807, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

releasing-reef 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 10d 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/releasing-reef/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing reef

Reef releases are driven by git tags matching v*. Pushing such a tag is the single trigger for .github/workflows/release.yml, which does the rest automatically: reef + reef-agent binaries for five targets, npm publish of @reef-tui/cli + five platform subpackages, GitHub Release with assets. You never run cargo publish, never npm publish by hand, never upload binaries manually. The contract is bump Cargo.toml, commit, tag, push.

What a v* tag push actually runs

.github/workflows/release.yml:

  1. Build matrix — for each target, builds reef-agent first, then reef (cargo build --release --locked -p <crate>). reef-agent goes first because reef-io's build script embeds the freshly-built agent as the upload-fallback blob. Targets:

    • aarch64-apple-darwin, x86_64-apple-darwin
    • x86_64-unknown-linux-gnu, aarch64-unknown-linux-gnu (via cross)
    • x86_64-pc-windows-msvc

    Each row uploads two artifacts: reef-<platform> and reef-agent-<platform>.

  2. npm platform subpackages — publishes @reef-tui/cli-{darwin-arm64,darwin-x64,linux-arm64,linux-x64,win32-x64}. Each subpackage bundles only the reef binary (the agent is embedded inside it). Each subpackage's package.json version is overwritten at publish time to ${TAG#v}.

  3. npm main package — publishes @reef-tui/cli with optionalDependencies pinned to the same version.

  4. GitHub Release — via softprops/action-gh-release@v2:

    • Attaches ten archives — reef-{darwin-arm64,darwin-x64,linux-arm64,linux-x64}.tar.gz + reef-win32-x64.zip, and the same set prefixed reef-agent-. The standalone agent archives are for users running it outside the upload-fallback path (e.g. preseeding it on a remote host).
    • Has generate_release_notes: true — this appends auto-generated ## What's Changed notes to whatever body the release already has; it does not overwrite a pre-existing body.

Implications:

  • The source package.json versions (0.0.0) are placeholders — the tag is authoritative for npm.
  • Deleting a tag after push does not unpublish npm packages. You have a 72h unpublish window on npm; beyond that, cut a patch release.
  • NPM_TOKEN repo secret must be valid. Expired token → silent failure on npm steps while the GitHub Release still succeeds.

Read the full file on GitHub · 210 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. 10d ago First seen · 210 lines · 162 tokens per session scan A dad84d0c9807

Subscribe to this mod's changes

releasing-reef is a skill published in the GitHub repository Blushyes/reef (81 stars, last pushed 15d ago), licensed Apache-2.0. It adds 162 tokens to every session and 3,007 once invoked, about $0.0008 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.

Claude CodeGit and workflowReleasesaiai-coding
Related

Other skills, from other repositories

release-jetbrains

Use when releasing the Kilo JetBrains plugin -- resolve a version ("next rc" or explicit), run the prepare workflow, edit and commit a filtered human-readable changelog on the release PR, then watch publish to completion.

Kilo-Org/kilocode · 50 tokens

finishing-a-development-branch

A process for finishing a completed development branch. A branch is a separate line of code changes that can later be merged or submitted as a pull request.

jnMetaCode/superpowers-zh · 25 tokens

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is…

GCWing/BitFun · 105 tokens

goal-issues-and-release

Clear the open issue backlog and then cut a release, in one autonomous run: use the batch-all-issues skill to resolve every open issue, then the goal-release skill to draft, merge, and see the release through publication. Never asks the user anything — every decision is made autonomously, and blockers are reported at…

dyoshikawa/rulesync · 83 tokens

goal-release

Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the Homebrew formula from the published release assets. Use when the user wants to draft and merge a release in one go, or…

dyoshikawa/rulesync · 86 tokens

merge-pr

Merge a pull request using gh pr merge --admin.

dyoshikawa/rulesync · 13 tokens