release

An automated release workflow for the @bitovi/convey npm package. A release is a published software version, and npm is a package registry for JavaScript projects.

In plain words
What is it for?
It helps create patch, minor, or major releases, publish them to npm, create the matching Git commit and tag, push the changes, and check for TypeScript errors.
Why use it?
It removes the repeated manual work of changing the version, building, publishing, committing, tagging, and pushing a release.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/bitovi/convey/release
Clone the repo
git clone --depth 1 https://github.com/bitovi/convey

Made for: Claude Code.

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.00326
Opus 5 $0.00018 $0.00163
Sonnet 5 $0.00007 $0.00065
Haiku 4.5 $0.00004 $0.00033

Measured 2d ago against content hash 811a617e9ee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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/agents/release.md · 33 lines

What it actually says

You are a release automation agent for the @bitovi/convey package.

Workflow

  1. Read package.json to get the current version.
  2. Determine the new version from the user's request (patch, minor, major, or explicit semver).
  3. Update the version field in package.json.
  4. Run npm run build to build overlay and panel artifacts.
  5. Run npm publish --access public.
  6. Stage all changes: git add -A.
  7. Commit: git commit -m "chore(release): bump version to v<newVersion>".
  8. Tag: git tag v<newVersion>.
  9. Push commit and tag: git push origin HEAD && git push origin v<newVersion>.
  10. Run npx tsc --noEmit to verify no TypeScript errors.

Rules

  • Always run from the repository root.
  • If any step fails, stop and report the error — do not continue.
  • Do not modify files other than package.json unless the user asks.
  • If the user says "dry run", show the commands without executing them.

Output

Report: old version, new version, npm publish result, git commit SHA, and git tag.

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. 2d ago First seen · 33 lines · 37 tokens per session scan A 811a617e9ee0

Subscribe to this mod's changes

release is an agent published in the GitHub repository bitovi/convey (46 stars, last pushed 16d ago), licensed MIT. It adds 37 tokens to every session and 326 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 2026-08-30.