nightly-docs-and-changelog

nightly-docs-and-changelog is a skill for Claude Code from ivy00johns/Skill-Madness. It costs 212 tokens per session (2,838 once invoked), scanned A, original, MIT.

A scheduled workflow that compares recent code changes with the project documentation, updates outdated documentation, records user-relevant changes in CHANGELOG.md, and opens one pull request.

In plain words
What is it for?
Use it for nightly documentation maintenance and changelog updates across the parts of a repository changed since the previous run.
Why use it?
It prevents documentation and the change history from falling behind as the code changes. A pull request gives a human a chance to review the updates.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the skill-madness plugin — 80 skills shipped together

Good fit Use it for nightly documentation maintenance and changelog updates across the parts of a repository changed since the previous run.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ivy00johns/skill-madness/nightly-docs-and-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 ivy00johns/Skill-Madness --skill nightly-docs-and-changelog
Clone the repo
git clone --depth 1 https://github.com/ivy00johns/Skill-Madness

Made for: Claude Code.

Or install skill-madness, the plugin that ships this one along with the rest of its 80 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 nightly-docs-and-changelog

README.md
[![agentmods](https://agentmods.dev/badge/skills/ivy00johns/skill-madness/nightly-docs-and-changelog/github.svg)](https://agentmods.dev/skills/ivy00johns/skill-madness/nightly-docs-and-changelog)
Your own site
<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/nightly-docs-and-changelog"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/nightly-docs-and-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 nightly-docs-and-changelog

Your own site · 80×15
<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/nightly-docs-and-changelog"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/nightly-docs-and-changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 212 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,838 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 $0.00212 $0.02838
Opus 5 $0.00106 $0.01419
Sonnet 5 $0.00042 $0.00568
Haiku 4.5 $0.00021 $0.00284

Measured 12d ago against content hash 3c31ed121f58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nightly-docs-and-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 12d 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/loops/nightly-docs-and-changelog/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nightly-docs-and-changelog

A configuration of [loop-controller]. That skill supplies the loop machinery — primitive selection, the full guardrail stack, state externalization. This skill supplies the three things specific to "keep an existing repo's docs+changelog from rotting on a nightly cadence": the per-night recipe (it diffs since the last run and authors the doc + changelog updates for that surface itself, following the documentation conventions [docs-agent] defines — docs-agent is the orchestrator's build-phase role and is not user-invocable on a schedule), the mechanical proof (docs match the changed surface AND every user-relevant change is recorded, ending in a reviewable PR), and the HITL boundary (it opens a PR and stops — it never merges docs). Read loop-controller for the guardrails; they're inherited, not repeated here.

Why disable-model-invocation: this loop edits docs, writes the changelog, commits, and opens a PR on its own, on a schedule. It is user-scheduled — you set it up once (or type /nightly-docs-and-changelog), not have Claude silently start rewriting docs because some code changed during the day.

The 5-part contract

Part This loop
trigger a nightly cron fire from the scheduled routine (default ~02:00 local), or an explicit /nightly-docs-and-changelog to run one sweep now
action ONE sweep: read the last-run marker → git diff <marker>..HEAD → for the changed surface, author the doc updates yourself (following [docs-agent]'s conventions) → classify each change user-relevant vs internal → append user-relevant ones to CHANGELOG.md (or write a no-change record) → advance the marker → open ONE PR via [git-pr]
proof the docs for the changed surface match the current implementation AND every user-relevant change since the marker is recorded in CHANGELOG.md (or a no-change night is recorded), surfaced as a reviewable docs/changelog diff + PR — default-FAIL: assume docs are stale and the changelog incomplete until verified against the diff since the last run
memory the last-run marker (a git tag/ref or .claude/docs-sweep-last), CHANGELOG.md, git history, and the open PR thread — all durable across nightly fires and laptop-off gaps
stop proof met → PR opened (then HITL — stop, never merge) OR no diff since the marker (record a no-change night, no PR) OR iteration/pass cap OR no-progress for 3 nights (same surface still drifting) OR budget cap OR an HITL checkpoint is hit

Read the full file on GitHub · 189 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. 12d ago First seen · 189 lines · 212 tokens per session scan A 3c31ed121f58

Subscribe to this mod's changes

nightly-docs-and-changelog is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed yesterday), licensed MIT. It adds 212 tokens to every session and 2,838 once invoked, about $0.0011 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.