refresh

refresh is a skill for Claude Code, Codex from tony/skills. It costs 22 tokens per session (1,395 once invoked), scanned A, a copy of changelog-refresh, MIT.

A Git workflow command that updates only the changelog entries added by the current branch so they describe the branch's final changes.

In plain words
What is it for?
Use it after a branch changes direction or its implementation no longer matches its changelog entries. It helps keep release notes accurate without rewriting history.
Why use it?
It removes the need to manually find and correct outdated changelog text while protecting entries inherited from the base branch. It can either leave the edit for review or make a new commit.

Skill for Claude CodeCodex

Part of the changelog plugin — 2 skills shipped together

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

Made for: Claude Code, Codex.

Or install changelog, the plugin that ships this one along with the rest of its 2 skills.

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 refresh

README.md
[![agentmods](https://agentmods.dev/badge/skills/tony/skills/refresh.svg)](https://agentmods.dev/skills/tony/skills/refresh)
Your own site
<a href="https://agentmods.dev/skills/tony/skills/refresh"><img src="https://agentmods.dev/badge/skills/tony/skills/refresh.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,395 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00022 $0.01395
Opus 5 $0.00011 $0.00698
Sonnet 5 $0.00004 $0.00279
Haiku 4.5 $0.00002 $0.00139

Measured yesterday against content hash 652af6c61f34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refresh 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 yesterday.

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.

Origin

This is a copy

89% identical to changelog-refresh — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/changelog/skills/refresh/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refresh Changelog Entries

Bring the changelog entries this branch introduced back in sync with what the branch currently does. With --commit, the correction lands as a new commit stacked on top; otherwise the edit is left uncommitted for the user to commit, like /changelog. History is never rewritten — for that, use /changelog:rewrite-aggressively.

Hard scope rule: this command only ever edits changelog content the branch itself added. Entries that came from the base branch — earlier releases, or unreleased entries from other work — are read-only. If a correction would require touching a line the branch didn't add, stop and ask.

Additional context from user: $ARGUMENTS


Phase 1: Establish scope

  1. Detect the base. If the branch has a PR (gh pr view --json baseRefName), the base is its baseRefName — stack-aware. Otherwise detect trunk via git symbolic-ref refs/remotes/origin/HEAD (fall back to master). If currently on the base/trunk itself, report and stop.

  2. Find the changelog file the same way /changelog does (scan for CHANGES, CHANGES.md, CHANGELOG.md, HISTORY.md, NEWS.md, …). No changelog changes on this branch and no changelog file → suggest /changelog instead and stop.

  3. Extract the branch's changelog footprint:

    git diff origin/<base>...HEAD -- <changelog-file>
    

    The added lines are the branch-owned entries — the only region this command may edit. Also list the branch commits touching the file:

    git log origin/<base>..HEAD --oneline -- <changelog-file>
    

    If the branch has no changelog commits yet, say so and offer to generate entries via the /changelog procedure instead.

Phase 2: Recompute what the entries should say

Read the sibling command file ../changelog/SKILL.md and apply its rules verbatim — the Core Constraint (a branch is not a release), Phase 1 convention detection, Phase 2 commit categorization, and Phase 3 entry generation and voice. Generate, from the branch's current net change (git log / git diff against origin/<base>), the entries the branch should have.

Read the full file on GitHub · 128 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. yesterday First seen · 128 lines · 22 tokens per session scan A 652af6c61f34

Subscribe to this mod's changes

refresh is a skill published in the GitHub repository tony/skills (2 stars, last pushed 6d ago), licensed MIT. It adds 22 tokens to every session and 1,395 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to changelog-refresh, differing in 28 lines, and is treated as a copy.

Related

Other skills, from other repositories

specify-factory

Decompose a multi-feature or multi-component specification into factory-consumable artifacts. Use this for high-complexity work — multiple features, three or more components, or parallel-eligible workstreams.

rsmdt/the-startup · 45 tokens

debug

Systematically diagnose and resolve bugs through conversational investigation and root cause analysis.

rsmdt/the-startup · 15 tokens

specify-incremental

Decompose a single-feature specification into a linear, phase-by-phase implementation plan. Use this for medium-complexity work — single feature, one or two components — where transparent human-in-the-loop phase review is preferred over factory automation.

rsmdt/the-startup · 53 tokens

validate

Validate in any of six modes — spec quality, single-file review, spec-to-implementation drift, constitution rule enforcement, comparison between two artifacts, or sanity-checking your understanding. Use when checking a spec by ID, validating a file by path, detecting drift, enforcing constitution rules, comparing two…

rsmdt/the-startup · 77 tokens

pattern-detection

Identify existing codebase patterns (naming conventions, architectural patterns, testing patterns) to maintain consistency. Use when generating code, reviewing changes, or understanding established practices.

rsmdt/the-startup · 37 tokens

requirements-elicitation

Requirement gathering techniques, stakeholder analysis, user story patterns, and specification validation. Use when clarifying vague requirements, resolving conflicting needs, documenting specifications, or validating requirements with stakeholders.

rsmdt/the-startup · 40 tokens