Agent skill

Update Claude

by MillenniumDawn in MillenniumDawn/Millennium-Dawn

Summarize the current session and propose improvements to CLAUDE.md, rules, docs, and skills, applying them after user confirmation.

CC-BY-SA-4.0Auto-check passedAgent Workflows

Install Update Claude

skills CLI
$ npx skills add MillenniumDawn/Millennium-Dawn --skill update-claude -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install MillenniumDawn/Millennium-Dawn update-claude --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/MillenniumDawn/Millennium-Dawn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/update-claude .claude/skills/update-claude && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
update-claude
GitHub stars
139
Token cost
~1k tokens
SKILL.md length
445 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
CC-BY-SA-4.0

At a glance

Summarize the current session and propose improvements to CLAUDE.md, rules, docs, and skills, applying them after user confirmation.

  • Works in 5 steps: Summarize the session → Identify generalizable improvements → Check existing documentation for staleness → …
  • Tasks that involve Agent instruction files
  • SKILL.md covers Placement rules, Execution and Important Notes
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Update Claude is an agent skill from MillenniumDawn/Millennium-Dawn. Summarize the current session and propose improvements to CLAUDE.md, rules, docs, and skills, applying them after user confirmation. Use only when explicitly invoked.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: Millennium Dawn and it's codebase. The licence is CC-BY-SA-4.0.

When your agent uses it

  • Tasks that involve Agent instruction files

Example prompts

  • “/update-claude”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Summarize the session
  2. Identify generalizable improvements
  3. Check existing documentation for staleness
  4. Propose changes
  5. Apply changes (with confirmation)

What it can do on your machine

Read from SKILL.md and the folder at commit 5abce3e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Update Claude loads about 1k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 445 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from MillenniumDawn/Millennium-Dawn at commit 5abce3e, republished under its CC-BY-SA-4.0 licence (© MillenniumDawn). 445 words, ~1,010 tokens.

Download SKILL.mdSave it as .claude/skills/update-claude/SKILL.md (or your agent's skills folder).
name
update-claude
description
Summarize the current session and propose improvements to CLAUDE.md, rules, docs, and skills, applying them after user confirmation. Use only when explicitly invoked.
disable-model-invocation
true

Summarize the current conversation and propose improvements to CLAUDE.md, rules, and skills.

Syntax: /update-claude

Placement rules

  • One home per rule: grep .claude/ for an existing statement before adding anywhere; extend the existing home, and put at most a one-line pointer elsewhere.
  • Always-loaded files (CLAUDE.md, AGENTS.md, .claude/rules/*.md without paths: frontmatter) hold only high-frequency, broadly-applicable rules in <=2 lines; worked examples and niche topics go to .claude/docs/.
  • Every new .claude/docs file must be added to .claude/docs/documentation-references.md.
  • Backlogs, finding counts, and change history go in a GitHub issue or the commit message, never in a doc.
  • New skills need frontmatter (name + a trigger-quality description); never add tables duplicating harness-injected lists.
  • Topic guidance that should auto-load for certain files → .claude/rules/*.md with paths: glob frontmatter.

Execution

1. Summarize the session

Review the full conversation and extract:

  • What was built or changed — new files, refactored systems, validator additions, etc.
  • Patterns discovered — recurring issues, anti-patterns, common mistakes found during the work.
  • Rules applied or created — coding conventions, scripting patterns, or process rules that emerged.
  • Decisions made — architectural choices, tradeoffs, why something was done a certain way.
2. Identify generalizable improvements

For each pattern or rule, assess whether it applies broadly or only to the specific task:

  • Essential shared guardrails → AGENTS.md, with no implementation recipes
  • Scripting and tooling details → the existing domain reference or tools/README.md
  • Player/contributor guidance → the appropriate existing page under docs/src/content/
  • Task-based reading pointers → .claude/rules/ or AGENTS.md
  • Skill improvements → .claude/skills/*/SKILL.md
  • Project context (non-obvious, persists across sessions) → memory

Filter ruthlessly — only propose additions that:

  1. Cannot be derived by reading the current codebase
  2. Would prevent a future mistake or speed up future work
  3. Are general enough to apply beyond the specific files touched
Show full SKILL.md (167 more words)Show less
3. Check existing documentation for staleness

Read the current state of:

  • CLAUDE.md and AGENTS.md routing: do their pointers still reach the right guidance?
  • Always-loaded files (AGENTS.md, unscoped .claude/rules/*.md): has implementation detail crept back in?
  • .claude/docs/localisation-rules.md — any gaps?
  • AGENTS.md — any conventions needing updates?

Flag anything outdated or contradicting current practice.

4. Propose changes

Lead with the recommended change in BLUF style. Include only applicable sections:

## Rules to add/update
- [file] — [what to add] — [why]

## Skills to add/update
- [skill name] — [what changed] — [why]

## Documentation to update
- [file] — [what's stale] — [what it should say]

## Memory to save
- [type] — [content] — [why it matters for future sessions]
5. Apply changes (with confirmation)

After presenting the proposals, ask the user which to apply. Then:

  • Edit the relevant files directly
  • Update the documentation index and task pointers when destinations change
  • Save any memory items

Important Notes

  • Do NOT add implementation details, file paths, or architecture derivable from reading the code.
  • Do NOT duplicate what's already in AGENTS.md or existing rules files.
  • Focus on why not what — rules should explain the reasoning so edge cases can be judged.
  • Keep rules concise — one pattern per entry, with a wrong/right example where helpful.
  • Check for conflicts before adding — grep the rules files to avoid contradictions.

© MillenniumDawn, CC-BY-SA-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/update-claude of MillenniumDawn/Millennium-Dawn.

Open the folder on GitHubat commit 5abce3e

Compare with similar skills

Update Claude next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Update Claude compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update Claude this skillMillenniumDawn/Millennium-Dawn139—~1kAutomated safety check: PassCC-BY-SA-4.0
Using Agent Skillsaddyosmani/agent-skills103k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.7k2 repos~627Automated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k18 repos~2.7kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    103k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed
  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.7k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 18 repos~2.7k tokens
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from MillenniumDawn/Millennium-Dawn

All 24 skills in this repo
  • Country AI Path

    MillenniumDawn/Millennium-Dawn

    Build or standardise one country's TAGaibehavior AI path game rule — write the rule options and loc, wire the global flags, own the focus weights, run the AI hardening pass, and open the PR.

    139 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Md Tick Profiler

    MillenniumDawn/Millennium-Dawn

    Profile MD's recurring per-tick scripted workload (the daily/weekly/monthly onaction hooks and everything they run) as a flamegraph sized by script ops, plus a text report.

    139 GitHub stars~816 tokensUpdated today
    Auto-check: notes
  • Add Leader

    MillenniumDawn/Millennium-Dawn

    Scaffold generals, field marshals, and admirals for a country using the MD count formulas and region skill ranges, writing character and recruitcharacter entries.

    139 GitHub stars~717 tokensUpdated today
    Auto-check passed
  • Additional Income

    MillenniumDawn/Millennium-Dawn

    Wire a country-specific income or expense stream into the MD money system: calculation block, hidden tooltip idea, loc key, and granting effect.

    139 GitHub stars~664 tokensUpdated today
    Auto-check passed
  • Dev Diary Mdx

    MillenniumDawn/Millennium-Dawn

    Convert a Millennium Dawn dev diary .docx into a publish-ready .mdx for the docs site: frontmatter, headers, and images placed in reading order, with the author's voice preserved.

    139 GitHub stars~958 tokensUpdated today
    Auto-check passed
  • Fix Issue

    MillenniumDawn/Millennium-Dawn

    Find an actionable open GitHub issue (or take an issue number or quoted task), implement the fix, commit, update the changelog, and open or update a PR.

    139 GitHub stars~988 tokensUpdated today
    Auto-check passed

Categories

Questions about Update Claude

What does Update Claude do?

Summarize the current session and propose improvements to CLAUDE.md, rules, docs, and skills, applying them after user confirmation. Update Claude is an agent skill from MillenniumDawn/Millennium-Dawn.md, rules, docs, and skills, applying them after user confirmation.

When should I use Update Claude?

Update Claude fits situations like: tasks that involve Agent instruction files.

How do I install Update Claude in Claude Code?

Run `npx skills add MillenniumDawn/Millennium-Dawn --skill update-claude -a claude-code`. Or copy the skill folder (.claude/skills/update-claude in MillenniumDawn/Millennium-Dawn) into .claude/skills/update-claude in your project. Claude Code loads it when a task matches its description.

How do I install Update Claude in Codex?

Run `npx skills add MillenniumDawn/Millennium-Dawn --skill update-claude -a codex`. Or copy the skill folder (.claude/skills/update-claude in MillenniumDawn/Millennium-Dawn) into .agents/skills/update-claude in your project. Codex loads it when a task matches its description.

Can I use Update Claude in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MillenniumDawn/Millennium-Dawn --skill update-claude -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-claude, .gemini/skills/update-claude, .github/skills/update-claude and .opencode/skills/update-claude in your project.

What does Update Claude need to run?

SKILL.md names no scripts, command-line tools or credentials: Update Claude is instructions for the agent only.

Does Update Claude access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Update Claude safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Update Claude use?

Update Claude is published under the CC-BY-SA-4.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Update Claude use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Update Claude?

Skills that share tags, products or a category with Update Claude: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars) and Writing For Agents (bestofjs/bestofjs, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update Claude?

MillenniumDawn (a GitHub organization) maintains it in MillenniumDawn/Millennium-Dawn, which has 139 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 9, 2026.

Source: MillenniumDawn/Millennium-Dawn on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.