New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Refresh Agents

by UniClipboard in UniClipboard/UniClipboard

Refresh fact-based sections of crates/AGENTS.md (STRUCTURE, WHERE TO LOOK, COMPLEXITY HOTSPOTS, KNOWN BROKEN) from current codebase state.

AGPL-3.0Auto-check passedAgent Workflows

Install Refresh Agents

skills CLI
$ npx skills add UniClipboard/UniClipboard --skill refresh-agents -a claude-code

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

GitHub CLI
$ gh skill install UniClipboard/UniClipboard refresh-agents --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/UniClipboard/UniClipboard.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/refresh-agents .claude/skills/refresh-agents && 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
refresh-agents
GitHub stars
1.9k
Token cost
~837 tokens
SKILL.md length
322 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Refresh fact-based sections of crates/AGENTS.md (STRUCTURE, WHERE TO LOOK, COMPLEXITY HOTSPOTS, KNOWN BROKEN) from current codebase state.

  • Works in 6 steps: Refresh STRUCTURE → Refresh WHERE TO LOOK → Refresh COMPLEXITY HOTSPOTS → …
  • Tasks that involve Agent instruction files
  • SKILL.md covers When to Use, Procedure, What NOT to change and Output
  • Calls git, node and cargo

What it does

Refresh Agents is an agent skill from UniClipboard/UniClipboard. Refresh fact-based sections of crates/AGENTS.md (STRUCTURE, WHERE TO LOOK, COMPLEXITY HOTSPOTS, KNOWN BROKEN) from current codebase state. Use after refactoring, renaming files, adding crates, or when the agent notices AGENTS.md info is stale.

Its SKILL.md is about 840 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 and Refactoring. The repository describes itself as: Real-time clipboard sync across all your devices — local-first, peer-to-peer, and end-to-end encrypted. No account. No cloud dependency. No central server. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Agent instruction files
  • Tasks that involve Refactoring

Example prompts

  • “/refresh-agents”

Workflow steps

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

  1. Refresh STRUCTURE
  2. Refresh WHERE TO LOOK
  3. Refresh COMPLEXITY HOTSPOTS
  4. Refresh KNOWN BROKEN (optional)
  5. Update datestamp
  6. Commit

What it can do on your machine

Read from SKILL.md and the folder at commit 101ffb3. 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

    Shell commands in SKILL.md call:

    • git
    • node
    • cargo

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Refresh Agents loads about 837 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 322 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~837

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 UniClipboard/UniClipboard at commit 101ffb3, republished under its AGPL-3.0 licence (© UniClipboard). 322 words, ~837 tokens.

Download SKILL.mdSave it as .claude/skills/refresh-agents/SKILL.md (or your agent's skills folder).
name
refresh-agents
description
Refresh fact-based sections of crates/AGENTS.md (STRUCTURE, WHERE TO LOOK, COMPLEXITY HOTSPOTS, KNOWN BROKEN) from current codebase state. Use after refactoring, renaming files, adding crates, or when the agent notices AGENTS.md info is stale.

Refresh AGENTS.md

Bring the fact-based sections of crates/AGENTS.md up to date with the current codebase.

When to Use

  • After adding/removing/renaming crates (STRUCTURE — also handled by pre-commit hook)
  • After moving or renaming key files (WHERE TO LOOK)
  • Periodically or before a milestone (COMPLEXITY HOTSPOTS)
  • After discovering tests that are broken on HEAD (KNOWN BROKEN)
  • When you notice AGENTS.md references stale paths during a session

Procedure

Step 1 — Refresh STRUCTURE

Run the pre-commit script to sync crate inventory:

bash
node scripts$refresh-agents-structure.mjs
Step 2 — Refresh WHERE TO LOOK

Verify each entry in the ## WHERE TO LOOK table still points to an existing file:

bash

For each row in the table:

  1. Check if the file path still exists (e.g., crates/uc-desktop/src/runtime.rs)
  2. If moved/renamed, update the Location column
  3. If deleted with no replacement, remove the row
  4. If a new major entry point was added (e.g., new daemon binary, new CLI subcommand), add a row

Do NOT add every file — only keep entries for the ~10 most common "where do I start?" lookups.

Step 3 — Refresh COMPLEXITY HOTSPOTS

Compute current hotspots using git churn + file size:

bash
# Top 10 files by recent change frequency (last 30 commits)
git log --oneline -30 --name-only --pretty=format: -- 'crates/' | sort | uniq -c | sort -rn | head -10

# Files over 400 lines
find crates/ -name '*.rs' -exec wc -l {} + | sort -rn | head -15

Update ## COMPLEXITY HOTSPOTS with files that are BOTH large (>300 lines) AND frequently changed. Keep to 4-6 entries max. Format:

text
- `path/to/file.rs`: one-sentence description of why it's complex.
Step 4 — Refresh KNOWN BROKEN (optional)

Only update this if you know of currently-broken tests on HEAD:

bash
cargo test --workspace --lib --no-fail-fast 2>&1 | grep "FAILED\|error\[" | head -10

If failures exist that are known/accepted (not regressions), list them:

text
## KNOWN BROKEN
- `uc-daemon-local` auth.rs doctests: 7 tests, known broken since ADR-008 migration
- `uc-platform` effective_mime doctest: fixture issue, skip with --lib

If all tests pass, either remove the section or write "None currently known."

Step 5 — Update datestamp

Change the "Last refreshed" line at the top:

text
**Last refreshed:** YYYY-MM-DD (manual; <reason>)
Step 6 — Commit

Stage and commit the updated file:

bash
git add crates/AGENTS.md
git commit -m "docs(agents): refresh AGENTS.md fact sections"

What NOT to change

  • ## OVERVIEW — rarely changes; only update on major architecture shifts
  • ## CONVENTIONS — updated by /learn skill, not here
  • ## ANTI-PATTERNS — updated by /learn skill, not here
  • ## COMMANDS — only update if build system actually changed
  • ## NOTES — historical notes, leave as-is unless clearly wrong

Output

Report what changed:

  • Which sections were updated
  • How many entries were added/removed/modified
  • Any stale entries that were removed

© UniClipboard, AGPL-3.0. 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 .agents/skills/refresh-agents of UniClipboard/UniClipboard.

Open the folder on GitHubat commit 101ffb3

Compare with similar skills

Refresh Agents 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.

Refresh Agents compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Refresh Agents this skillUniClipboard/UniClipboard1.9k—~837Automated safety check: PassAGPL-3.0
Docslatitude-dev/latitude-llm4.7k—~2.5kAutomated safety check: PassMIT
Steadyagent WorkflowKhalilzhang0825/boring-is-all-you-need173—~1kAutomated safety check: PassMIT
Update Docspeterkrueck/Claude-Code-Development-Kit1.4k—~2.7kAutomated safety check: PassMIT
Claude Md Writerserejaris/personal-corp-os229—~1.6kAutomated safety check: PassMIT
Refactor Memoryvinta/hal-9000138—~887Automated safety check: PassMIT

Similar skills

  • Docs

    latitude-dev/latitude-llm

    Review the current conversation context and git changes, then persist durable repository knowledge into dev-docs/.md by domain and into AGENTS.md for cross-cutting repo rules.

    4.7k GitHub stars~2.5k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Steadyagent Workflow

    Khalilzhang0825/boring-is-all-you-need

    Local-first Codex workflow for planning, debugging, reviewing, refactoring, improving AGENTS.md, building skills, publishing agent harness repositories, or running complex multi-step coding tasks…

    173 GitHub stars~1k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Update Docs

    peterkrueck/Claude-Code-Development-Kit

    Update project documentation after code changes. An agent skill from peterkrueck/Claude-Code-Development-Kit.

    1.4k GitHub stars~2.7k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Claude Md Writer

    serejaris/personal-corp-os

    A skill your agent uses when creating or refactoring CLAUDE.md files - enforces best practices for size, structure, and content organization

    229 GitHub stars~1.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Refactor Memory

    vinta/hal-9000

    A skill your agent uses when refactoring Claude Code or Codex memories to remove stale or derivable entries, resolve contradictions, promote standing instructions, or reorganize recall.

    138 GitHub stars~887 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Mcaf Solid Maintainability

    managedcode/Storage

    Apply SOLID, SRP, cohesion, composition-over-inheritance, and small-file discipline to code changes.

    138 GitHub stars~1.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from UniClipboard/UniClipboard

All 24 skills in this repo

  • Beui

    UniClipboard/UniClipboard

    Pick and install beUI (@beui) animated React components from the shadcn registry.

    1.9k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Create PR

    UniClipboard/UniClipboard

    Push the current branch and open a GitHub pull request against main.

    1.9k GitHub stars~4.6k tokensUpdated today
    Auto-check passed

  • Design Audit

    UniClipboard/UniClipboard

    定期审计代码库的工程设计问题（高心智复杂度、单一真相源被破坏、catch-all 胖接口、死代码、散落魔法字面量、泄漏抽象、资源生命周期靠环形缓冲）与可优化点，范围限定为自上次审计以来的 git churn，每条发现都落到 file:line 并对照本项目自己的 VISION.md / 各级 AGENTS.md / memory…

    1.9k GitHub stars~554 tokensUpdated today
    Auto-check passed

  • Dual Side Debug

    UniClipboard/UniClipboard

    Inspect uniclipboard logs from BOTH the macOS host and the mounted Windows peer when debugging cross-platform sync, pairing, transfer, or daemon issues.

    1.9k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • E2E Test Thinker

    UniClipboard/UniClipboard

    Analyze the current branch's diff against main and determine which changes are testable via CLI-based end-to-end tests.

    1.9k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • iOS Log Diagnose

    UniClipboard/UniClipboard

    Drive the UniClipboard iOS app in a simulator and read its OSLog yourself to diagnose a mobile-sync bug, instead of asking the user to paste logs.

    1.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Refresh Agents

What does Refresh Agents do?

Refresh fact-based sections of crates/AGENTS.md (STRUCTURE, WHERE TO LOOK, COMPLEXITY HOTSPOTS, KNOWN BROKEN) from current codebase state. Refresh Agents is an agent skill from UniClipboard/UniClipboard.md (STRUCTURE, WHERE TO LOOK, COMPLEXITY HOTSPOTS, KNOWN BROKEN) from current codebase state.

When should I use Refresh Agents?

Refresh Agents fits situations like: tasks that involve Agent instruction files; tasks that involve Refactoring.

How do I install Refresh Agents in Claude Code?

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

How do I install Refresh Agents in Codex?

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

Can I use Refresh Agents 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 UniClipboard/UniClipboard --skill refresh-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/refresh-agents, .gemini/skills/refresh-agents, .github/skills/refresh-agents and .opencode/skills/refresh-agents in your project.

What does Refresh Agents need to run?

Going by SKILL.md and its folder, Refresh Agents needs the command-line tools its instructions call (git, node and cargo).

Does Refresh Agents access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Refresh Agents 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 Refresh Agents use?

Refresh Agents is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Refresh Agents use?

About 837 tokens (SKILL.md is roughly 3.3k 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 Refresh Agents?

Skills that share tags, products or a category with Refresh Agents: Docs (latitude-dev/latitude-llm, 4.7k stars), Steadyagent Workflow (Khalilzhang0825/boring-is-all-you-need, 173 stars), Update Docs (peterkrueck/Claude-Code-Development-Kit, 1.4k stars) and Claude Md Writer (serejaris/personal-corp-os, 229 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Refresh Agents?

UniClipboard (a GitHub organization) maintains it in UniClipboard/UniClipboard, which has 1,856 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.

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