update-changelog

update-changelog is a skill for Claude Code from AcKeskin/contexture. It costs 73 tokens per session (1,908 once invoked), scanned A, original, MIT.

A controlled writer for the project’s CHANGELOG.md, the file that records shipped changes in reverse date order.

In plain words
What is it for?
Use it to propose and confirm dated changelog entries after shipping a feature or making a significant planning change.
Why use it?
It keeps release history consistent and records completed work as meaningful shipped units instead of a noisy list of commits.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: mentions CLAUDE.md.

Good fit Use it to propose and confirm dated changelog entries after shipping a feature or making a significant planning change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ackeskin/contexture/update-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 AcKeskin/contexture --skill update-changelog
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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 update-changelog

README.md
[![agentmods](https://agentmods.dev/badge/skills/ackeskin/contexture/update-changelog.svg)](https://agentmods.dev/skills/ackeskin/contexture/update-changelog)
Your own site
<a href="https://agentmods.dev/skills/ackeskin/contexture/update-changelog"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/update-changelog.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,908 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 $0.00073 $0.01908
Opus 5 $0.00036 $0.00954
Sonnet 5 $0.00015 $0.00382
Haiku 4.5 $0.00007 $0.00191

Measured 4d ago against content hash 6dd33f4b6cee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

update-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 4d 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/update-changelog/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

update-changelog

The changelog writer. Maintains the canonical CHANGELOG.md — the single reverse-chronological "what actually happened" ship-record that cuts session re-alignment cost. It is the one writer; several caller skills offer it but never write the changelog themselves.

Prerequisite — load the format contract

Before composing or writing anything, Read docs/changelog-contract.md (location resolution, ordering, the unit of a line, the two line-types, the significant-change rule, voice). It is the authority; this skill applies it. Every reference below assumes you have read it this turn.

When to run

  • User types /update-changelog [unit description] (explicit trigger).
  • User says "log this ship", "record what shipped", "add this to the changelog".
  • Another skill offers it (the caller path): recap, checkpoint, execute, spec, draft-plan invite /update-changelog at a ship moment or a significant planning-artifact change. The caller surfaces the offer; the user accepts; this skill does the write. The skill is the writer, the callers are the doorways.
  • Otherwise never auto-fires. No session-start, no per-turn, no hook trigger. And it never auto-writes — the propose-confirm gate (§3) gates every line, even on the caller path.

Inputs

  1. The unit. Text after /update-changelog describes the shipped unit / significant change. No argument → infer from the recent turns (what was just shipped or decided); ask one clarifying question if multiple candidates.
  2. Line-type signal. From the trigger: a ship moment (execute-done / checkpoint / recap / close-out) → ship line (); a significant planning-artifact change (spec / envision / draft-plan) → decision line (). When invoked directly, infer from the unit; when ambiguous, ask.
  3. Target project. $CLAUDE_PROJECT_DIR if set, else cwd.

Procedure

1. Resolve the target CHANGELOG

Per the contract §1:

  • Project root CHANGELOG.md if it exists, or the project plainly declares one → use it.
  • Else .claude/CHANGELOG.md (create lazily on first accepted write).
  • State which file you will write to before proposing.
  • If the root CHANGELOG.md would be swallowed by a bare/global .gitignore rule (git check-ignore it), surface that to the user — do not edit .gitignore to force-track; syncing is the user's choice.

Read the full file on GitHub · 98 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. 4d ago First seen · 98 lines · 73 tokens per session scan A 6dd33f4b6cee

Subscribe to this mod's changes

update-changelog is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,908 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

github-release-management

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.

spencermarx/open-code-review · 27 tokens

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

release-notes

Draft short release notes from a list of changes. Use when the user asks for changelogs, release notes, or a concise product update.

cloudflare/agents · 33 tokens

github

Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.

AtomicBot-ai/atomic-agent · 48 tokens

create-milestone

Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.

agentic-community/mcp-gateway-registry · 64 tokens

pack-submit

Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.

aeonfun/aeon · 27 tokens