agentweaver: Skill for Claude Code

.copilot/skills/agentweaver-changelog/SKILL.md

agentweaver-changelog is a skill for Claude Code, Codex from sabbour/agentweaver. It costs 27 tokens per session (993 once invoked), scanned A, original, MIT.

A release workflow based on Changesets, a tool that records how a code change should affect version numbers and release notes. It manages release intent, previewing, preparation, publication, and changelog updates.

In plain words
What is it for?
Use it to add release notes for a pull request, choose a patch or minor version change, preview the next release, prepare a release branch, and validate version records.
Why use it?
It gives contributors a consistent way to describe release changes and keeps the product version, package files, and changelog aligned.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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

Reuse

Borrowing it

Nothing to install: this file belongs to sabbour/agentweaver. 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/sabbour/agentweaver/dev/.copilot/skills/agentweaver-changelog/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sabbour/agentweaver

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 agentweaver-changelog

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sabbour/agentweaver/agentweaver-changelog"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/agentweaver-changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 993 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.
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 $0.00027 $0.00993
Opus 5 $0.00014 $0.00496
Sonnet 5 $0.00005 $0.00199
Haiku 4.5 $0.00003 $0.00099

Measured 9d ago against content hash bbc9195bba97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agentweaver-changelog 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 9d 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.

.copilot/skills/agentweaver-changelog/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Agentweaver uses Changesets to turn reviewed, contributor-authored release intent into release metadata. It is a single-package adapter: the root private agentweaver package is the only selectable package. VERSION is the product-version source of truth; package.json.version and package-lock.json.packages[""].version must mirror it. @changesets/cli is pinned to the stable ^2.31.0 line, not the next prerelease tag.

Changeset lifecycle

  1. Add intent: for a user-facing PR, run npm run changeset, select agentweaver, choose the appropriate bump, and write user-facing prose. At 0.x, use patch for compatible fixes and minor for features or breaking changes. Reserve major for the deliberate release/v1.0.0 transition.
  2. Preview: run npm run changeset:status and npm run release:plan to inspect pending fragments and the calculated version before cutting the release branch.
  3. Prepare: only on a clean release/vX.Y.Z branch, run npm run release:prepare -- --expected X.Y.Z. It consumes the fragments, lets Changesets update package/lockfile versions and the matching CHANGELOG.md section, writes VERSION, and validates all version mirrors and the generated section.
  4. Promote: promote the prepared release branch to main through a green PR.
  5. Publish: from a clean checkout at the exact promoted main SHA, run npm run release:publish. It validates the prepared metadata and creates the annotated tag plus the GitHub Release from the exact matching changelog section. It does not calculate or commit a version, and it does not deploy anything.
  6. Deploy: deploy that published version with npm run azure:deploy-from-release -- vX.Y.Z. For the normal first shipment, npm run azure:release composes steps 5 and 6 in one command.
  7. Forward-port: before deleting the release branch, create a short-lived branch from current dev and run npm run release:sync-dev -- <prepare-sha>. Open and merge its PR to return the prepared metadata and consumed fragments to dev.

Read the full file on GitHub · 74 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. 9d ago First seen · 74 lines · 27 tokens per session scan A bbc9195bba97

Subscribe to this mod's changes

agentweaver-changelog is a skill published in the GitHub repository sabbour/agentweaver (5 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 993 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 2026-08-31.