phase: Skill for Claude Code

.claude/skills/changelog/SKILL.md

changelog is a skill for Claude Code, Codex from phase-rs/phase. It costs 55 tokens per session (1,813 once invoked), scanned A, original, Apache-2.0.

A tool for turning recent project commits into a Discord-ready What's New update. It selects commits from a specified reference, date, or previous changelog position.

In plain words
What is it for?
Use it to prepare release notes, recent-change summaries, or the next sequential changelog batch from the project's history.
Why use it?
It saves time when converting technical git history into a concise update for users or contributors.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: positional $N argument; mentions Codex.

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bun scripts/gen-changelog-meta.ts.

Reuse

Borrowing it

Nothing to install: this file belongs to phase-rs/phase. 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/phase-rs/phase/main/.claude/skills/changelog/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/phase-rs/phase

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 changelog

README.md
[![agentmods](https://agentmods.dev/badge/skills/phase-rs/phase/changelog.svg)](https://agentmods.dev/skills/phase-rs/phase/changelog)
Your own site
<a href="https://agentmods.dev/skills/phase-rs/phase/changelog"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/changelog.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,813 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 pass 7 Sept 2026
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 $0.00055 $0.01813
Opus 5 $0.00028 $0.00907
Sonnet 5 $0.00011 $0.00363
Haiku 4.5 $0.00006 $0.00181

Measured 8d ago against content hash b87f9c36947a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 8d 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/skills/changelog/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changelog

Generate a user-facing Discord changelog from git history. The input may be empty, a date/time, a commit ref, a tag, or a sequential "next batch" request.

Range Selection

Always run git fetch origin first and use origin/main unless the user names another branch.

Do not use git log --since as authoritative in this repo. Squash-merge commit dates are non-monotonic, and --since can silently drop commits. Use one of these methods:

  • Commit hash or tag: use graph reachability.
    git log --no-merges <ref>..origin/main --format="%h %s" | cat -n
    
  • Date/time: convert the user input to a Unix epoch yourself, then filter %ct.
    cutoff=$(date -j -f "%Y-%m-%dT%H:%M:%S %z" "2026-05-22T21:05:00 -0700" "+%s")
    git log origin/main --no-merges --format="%ct %cI %h %s" \
      | awk -v c="$cutoff" '$1 >= c' | sort -rn | cat -n
    
  • Empty input: default to the last seven days using the same epoch-filter method.

If no timezone is supplied, assume Mountain Time and state the offset used. Convert named timezones yourself before computing the epoch.

Commit Reading

Read commit bodies, not only subjects, for every non-obvious commit:

git show -s --format="%s%n%n%b" <hash>

Cross-check the final changelog against the full commit count so no commit is silently dropped.

Writing Rules

  • Output the changelog in a single fenced code block.
  • Start with 🎴 What's New in phase.rs.
  • Use emoji-headed sections only when they have content, usually in this order:
    • ✨ New Cards & Mechanics
    • 🛠️ Cards That Now Work Right
    • ⚔️ Combat & Gameplay
    • 🖥️ Interface
    • 🌍 Localization
    • Other sections such as 🤖 AI or 🌐 Multiplayer when warranted.
  • Use bullets.
  • Consolidate related commits; do not mirror commits one-to-one.
  • Use player-facing language. Avoid implementation descriptions unless needed for clarity.
  • Name concrete cards or mechanics in parentheses when helpful.
  • Order by user impact.
  • Omit internal-only changes unless they have visible impact.

Read the full file on GitHub · 157 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. 8d ago First seen · 157 lines · 55 tokens per session scan A b87f9c36947a

Subscribe to this mod's changes

changelog is a skill published in the GitHub repository phase-rs/phase (268 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,813 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

anarlog

Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.

fastrepl/anarlog · 44 tokens

issue-triage

Read all open issues (GitHub/GitLab), categorize by type and effort, plan batch implementation order, and coordinate implementation across multiple issues in a single PR/MR. Auto-detects platform from git remote. Use when asked to "implement all issues", "fix all open issues", "batch implement", or "address all…

d-oit/rust-2026-template · 102 tokens

atomic-commit

Atomic git workflow - validates, commits, pushes, creates PR/MR, and verifies CI with zero-warnings policy. Orchestrates complete code submission as state machine with rollback on failure. Supports GitHub (gh) and GitLab (glab). Triggers: "commit changes", "push and create PR", "submit code", "atomic commit".

d-oit/rust-2026-template · 76 tokens

self-fix-loop

Self-learning fix loop - commit, push, monitor CI, auto-fix failures using swarm agents with skills on demand, loop until all checks pass. Supports GitHub Actions and GitLab CI. Use when CI fails and you need to iteratively fix until green. Triggers: "fix CI", "loop until green", "auto-fix failures", "self-fix".

d-oit/rust-2026-template · 81 tokens

skillify

Auto-create new skills from repetitive workflows. When you notice yourself doing the same multi-step process repeatedly, extract it into a reusable SKILL.md that any agent can use.

DDS-Solutions/AI-TadPole-OS · 37 tokens

deployment-procedures

Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.

DDS-Solutions/AI-TadPole-OS · 29 tokens