clawdbot-feishu: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from m1heng/clawdbot-feishu. It costs 28 tokens per session (641 once invoked), scanned A, original, MIT.

A release workflow for publishing a new version of a Feishu plugin, a plugin for the Feishu collaboration platform. It covers version selection, type checking, release notes, npm publishing preparation, and a GitHub release.

In plain words
What is it for?
Use it to inspect changes since the last tag, update package.json, create a draft GitHub release, commit and tag the version, and publish the package to npm.
Why use it?
It provides a repeatable checklist for deciding whether a change is a patch, minor release, or breaking major release. It also prevents release work from continuing when the TypeScript check fails.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is m1heng/clawdbot-feishu's own configuration. It tells Claude Code how to work on clawdbot-feishu 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 clawdbot-feishu configures →

About the project

clawd-feishu is a channel plugin that connects OpenClaw to Feishu/Lark, a collaboration and messaging platform. OpenClaw users use it to interact with the agent through Feishu or Lark.

m1heng/clawdbot-feishu · 4,245 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to m1heng/clawdbot-feishu. 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/m1heng/clawdbot-feishu/main/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/m1heng/clawdbot-feishu

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/m1heng/clawdbot-feishu/release/github.svg)](https://agentmods.dev/skills/m1heng/clawdbot-feishu/release)
Your own site
<a href="https://agentmods.dev/skills/m1heng/clawdbot-feishu/release"><img src="https://agentmods.dev/badge/skills/m1heng/clawdbot-feishu/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/m1heng/clawdbot-feishu/release"><img src="https://agentmods.dev/badge/skills/m1heng/clawdbot-feishu/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 641 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 4
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 37
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
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 $0.00028 $0.00641
Opus 5 $0.00014 $0.00320
Sonnet 5 $0.00006 $0.00128
Haiku 4.5 $0.00003 $0.00064

Measured 10d ago against content hash 79484998c117, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 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.

.claude/skills/release/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Workflow

Publish a new version of @m1heng-clawd/feishu to npm and create a GitHub release.

Prerequisites

  • Working tree is clean (all changes committed to main)
  • npm login session is active with publish access to @m1heng-clawd scope
  • gh CLI is authenticated

Steps

1. Determine version bump

Check what changed since the last release:

# Find latest release tag
gh release list --limit 1

# Review commits and diff stat
git log <last-tag>..HEAD --oneline
git diff <last-tag>..HEAD --stat

Choose bump type: patch (bug fixes), minor (new features), or major (breaking changes).

2. Type check

npx tsc --noEmit

Do NOT proceed if type check fails.

3. Draft release notes

Review the full diff to write release notes:

git diff <last-tag>..HEAD

Create a GitHub release draft first:

gh release create v<new-version> --draft --title "v<new-version>" --target main --notes "<release notes markdown>"

4. Bump version in package.json

Edit package.json to update the "version" field to <new-version>.

5. Commit, tag, and push

git add package.json
git commit -m "chore: bump version to <new-version>"
git tag v<new-version>
git push && git push --tags

6. Publish to npm

npm publish

If auth fails, ask the user to run npm login first, then retry.

7. Publish GitHub release

gh release edit v<new-version> --draft=false

Release Notes Format

Follow the established format (see previous releases for reference):

## Features

- **Feature title** — Description. (#PR)

## Bug Fixes

- **Fix title** — Description. (#PR)

## Internal

- Internal change description.

Troubleshooting

npm publish 404 / auth error

npm login          # re-authenticate
npm whoami         # verify logged in
npm publish        # retry

Tag already exists

If the tag was created but publish failed, delete and recreate after fixing:

Read the full file on GitHub · 120 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 · 120 lines · 28 tokens per session scan A 79484998c117

Subscribe to this mod's changes

release is a skill published in the GitHub repository m1heng/clawdbot-feishu (4,245 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 641 once invoked, about $0.0001 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.