com.doji.package-authoring: Skill for Codex

.codex/skills/package-changelog-writing/SKILL.md

package-changelog-writing is a skill for Codex from julienkay/com.doji.package-authoring. It costs 54 tokens per session (586 once invoked), scanned A, original, MIT.

A writing guide for recording changes to a Unity package in its changelog. A changelog is a dated or grouped list of user-facing updates in a software project.

In plain words
What is it for?
Use it when adding or revising entries for new package capabilities, generated output, public programming interfaces, and meaningful workflow changes.
Why use it?
It keeps release notes focused on changes package users actually receive instead of internal maintenance details or unrelated host-project work.

Skill for Codex

Written for Codex: installed under .codex/.

This is julienkay/com.doji.package-authoring's own configuration. It tells Codex how to work on com.doji.package-authoring 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 com.doji.package-authoring configures →

Reuse

Borrowing it

Nothing to install: this file belongs to julienkay/com.doji.package-authoring. 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/julienkay/com.doji.package-authoring/master/.codex/skills/package-changelog-writing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/julienkay/com.doji.package-authoring

Made for: 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 package-changelog-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/julienkay/com.doji.package-authoring/package-changelog-writing/github.svg)](https://agentmods.dev/skills/julienkay/com.doji.package-authoring/package-changelog-writing)
Your own site
<a href="https://agentmods.dev/skills/julienkay/com.doji.package-authoring/package-changelog-writing"><img src="https://agentmods.dev/badge/skills/julienkay/com.doji.package-authoring/package-changelog-writing/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 package-changelog-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/julienkay/com.doji.package-authoring/package-changelog-writing"><img src="https://agentmods.dev/badge/skills/julienkay/com.doji.package-authoring/package-changelog-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 586 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 $0.00054 $0.00586
Opus 5 $0.00027 $0.00293
Sonnet 5 $0.00011 $0.00117
Haiku 4.5 $0.00005 $0.00059

Measured 11d ago against content hash 8059326e1db1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

package-changelog-writing 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 11d 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.

.codex/skills/package-changelog-writing/SKILL.md · 52 lines

What it actually says

Package Changelog Writing

Use this skill for edits to com.doji.package-authoring/CHANGELOG.md.

Primary source of truth:

  • com.doji.package-authoring/CHANGELOG.md
  • the current package code under com.doji.package-authoring/

Scope rules:

  • Write changelog entries for the shipped package, not for the template host project, unless the host-project asset is part of the package-facing workflow.
  • Summarize user-facing package capabilities, generated output behavior, public API additions, and meaningful workflow changes.
  • Do not narrate internal refactors unless they affect package users, generated output, or the exposed scripting API.
  • Do not add bullets for documentation work, local tooling notes, or maintainer workflow changes unless those changes introduce a package-facing capability users actually receive.

Pre-1.0 release rule:

  • While the package is still preparing for its initial release, treat changelog edits as part of the upcoming release scope.
  • Do not invent release history that did not happen.
  • Avoid Changed language that implies an already released baseline unless the package actually shipped that earlier behavior.
  • Prefer folding new unreleased work into the upcoming release's Added section when the feature has not been released before.

Section choice rules:

  • Use Added for new user-visible capabilities, public APIs, new generated outputs, or new configuration surfaces.
  • Use Changed only when a previously released behavior was intentionally altered in a way users should know about.
  • Use Fixed only for regressions or incorrect released behavior.
  • Avoid filler sections when there is nothing meaningful to record there.

Writing rules:

  • Write for package users, not for commit history.
  • Prefer one concise bullet per distinct capability.
  • Do not split one package-facing feature into multiple bullets just because it introduced supporting types, helper models, or namespace cleanup.
  • Lead with the outcome, not implementation detail.
  • Name public namespaces, menu paths, generated file paths, or major outputs when they help users understand the change.
  • Keep bullets specific enough that a future reader can tell what shipped without reading the code.
  • Exclude package-maintainer housekeeping such as documentation additions, local build workflow notes, or process clarifications unless they change the shipped package experience.

Checks before finishing:

  • confirm each bullet matches current package behavior
  • confirm entries describe package-facing changes rather than editor-internal churn
  • confirm category choice (Added, Changed, Fixed) matches actual release state
  • for pre-1.0 work, confirm the entry reads like upcoming release scope rather than retroactive history
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. 11d ago First seen · 52 lines · 54 tokens per session scan A 8059326e1db1

Subscribe to this mod's changes

package-changelog-writing is a skill published in the GitHub repository julienkay/com.doji.package-authoring (5 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 586 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 2026-08-31.