changelog

changelog is a skill for Claude Code from mthines/agent-skills. It costs 123 tokens per session (3,895 once invoked), scanned A, original, MIT.

A Markdown work summary built from your recently merged or closed GitHub pull requests and Linear tickets. Linear is a tool for tracking development work.

In plain words
What is it for?
It creates a changelog for a chosen number of days, groups work by feature area, and can cover the current repository or all repositories where you authored pull requests.
Why use it?
It saves you from manually collecting recent work and organizing it into a readable update.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the mthines-agent-skills plugin — 55 skills, 4 agents shipped together

Good fit It creates a changelog for a chosen number of days, groups work by feature area, and can cover the current repository or all repositories where you authored pull requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mthines/agent-skills/changelog
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.

Any agent
npx skills add mthines/agent-skills --skill changelog
Clone the repo
git clone --depth 1 https://github.com/mthines/agent-skills

Made for: Claude Code.

Or install mthines-agent-skills, the plugin that ships this one along with the rest of its 55 skills, 4 agents.

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 changelog

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mthines/agent-skills/changelog"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,895 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 high

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 →

  • high System Prompt Leakage · line 61
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
  • high System Prompt Leakage · line 235
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 $0.00123 $0.03895
Opus 5 $0.00062 $0.01947
Sonnet 5 $0.00025 $0.00779
Haiku 4.5 $0.00012 $0.00390

Measured 9d ago against content hash 471ea4f4abb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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.

skills/delivery/changelog/SKILL.md · 393 lines

How it starts

The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changelog

Generate a markdown changelog of the current user's recent work — merged or closed pull requests, plus Linear tickets they closed or worked on — grouped by feature area. Render the result against the template in templates/changelog.md and print it to the chat.

Arguments

Three orthogonal arguments. Flag order is free. days is positional.

days (positional, optional)

Controls the window in days.

Input Resolved window
(none) 7 days, ending today (UTC)
14 14 days, ending today
30 30 days, ending today
Any non-integer Reject with an error; do not assume a value

--scope=current|all (default: current)

  • current (DEFAULT) — restrict PRs to the GitHub repo of the current working directory, resolved via gh repo view --json nameWithOwner -q .nameWithOwner. Linear tickets are not narrowed (Linear has no repo concept) — say so in the rendered output.
  • all — query every repo the user authored PRs in. Output is grouped by repo first, then by feature bucket inside each repo (see Output rules).

If --scope=current is passed but the cwd is not a GitHub-linked git repo, error and exit 1 — do not silently fall back to all. The error must read: Current directory is not a GitHub-linked git repo. Re-run with --scope=all or cd into a repo.

--audience=technical|general (default: technical)

  • technical (DEFAULT) — existing rendering: conventional-commit scopes as buckets, identifier-level summaries, full PR numbers inline.
  • general — re-render for a non-engineering audience (see Audience modes).

Argument parsing

Parse flags in any order; the first non-flag positional integer is days. Unknown flags must error. Compute the window once at start with:

Read the full file on GitHub · 393 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 393 lines · 123 tokens per session scan A 471ea4f4abb7

Subscribe to this mod's changes

changelog is a skill published in the GitHub repository mthines/agent-skills (13 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 3,895 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

meanest-editor

Roast a pitch or press release with the eye of a veteran PR director. Honest, sharp, constructive — never cruel for its own sake.

elvisun/newsjack · 33 tokens

headline-generator

Generate headline candidates from a story's raw facts: news-style headlines, press-release headlines, and pitch subject lines. A pure generation skill — it finds the charge in the facts, then runs ten proven moves (consequence, picture, number-as-hero, two-beat turn, naming, reader's-own-story, open question, voice…

elvisun/newsjack · 88 tokens

ai-visibility-writing

Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…

elvisun/newsjack · 137 tokens

cf-warm

Catch up after absence — summarize git history for a user. Triggers: "warm up", "catch me up", "what happened while I was away", "summarize recent changes", "what changed since I left".

dinhanhthi/coding-friend · 50 tokens

gh-pr-list

Generate a short, copy-paste friendly Slack message listing the user's open PRs in the current repo, split into "Ready for review" (non-draft) and "Drafts" sections, each as bullets with custom emoji and markdown-style links. Use when the user mentions PRs ready to review, Slack PR list, share my PRs on Slack, or…

tomimor/skills · 86 tokens

git-workflow-and-versioning

Guides git commit discipline, trunk-based branching, and semantic versioning/changelogs for released code, including Go modules' major-version import path rule. Use when committing, branching, resolving conflicts, cutting a release, choosing a semantic version bump, tagging a release, or writing a changelog entry.

shennawardana23/skillme · 68 tokens