[Resource]: agency-agents-fork

[daehounan]

Display Name

agency-agents-fork

Category

Agent Skills

Sub-Category

General

Primary Link

https://github.com/daehounan/agency-agents-fork

Author Name

daehounan

Author Link

https://github.com/daehounan

License

MIT

Other License

No response

Description

A user-level Claude Code config bundle: 163 specialist agent personas + 24 routing skills

• 16 NEXUS strategy playbooks. Fork of msitarzewski/agency-agents with China-market agents
  removed (22 files) and Korean + Japanese Business Navigators added.

Focused differentiators (since the list rightly leans against general marketplaces):

1. Korean Business Navigator and Japanese Business Navigator — 품의/nunchi/회식/카카오톡 and
   稟議/根回し/KY/飲み会/報連相 deal mechanics for foreign professionals. Each ~200 lines,
   no equivalent in any other public collection.

2. skill-routing-arbitrator meta-skill — disambiguates across ~500 skills in the wider
   Claude Code ecosystem (ecc:, anthropic-skills:, engineering:, design:, etc.). Encodes
   deterministic preferences per cluster (code review, security audit, MCP build, document
   formats, etc.).

3. Ecosystem-wide skill duplicates audit — docs/skill-ecosystem-duplicates.md maps the
   ecosystem into versioned snapshots, legacy shims, cross-namespace duplicates, and hooks.
   Useful for anyone trying to figure out which of several overlapping skills to use.

4. Cross-reference audit in CI — scripts/audit-agent-refs.ps1 verifies every backticked
   agent slug in every SKILL.md resolves to a real file. Currently 0 orphans across 24
   skills, 163 agents. Catches typos and stale refs before they ship.

5. Idempotent hook installer with settings backup and rollback — install-hooks-in-settings.ps1
   modifies ~/.claude/settings.json atomically with pre-write JSON validation, timestamped
   .bak file, and rollback on failure. Avoids the typical "I broke my settings.json" risk.

Security disclosure:

• Zero outbound network calls. Verified — none of the scripts or hooks call out to any URL.
• Does NOT require --dangerously-skip-permissions.
• Hooks are silent on error (try/catch with exit 0) so they never block tool execution.
• Telemetry hook records only timestamp + skill name + session id + args-present-boolean —
  no prompt content, no arg values.
• SECURITY.md documents the vulnerability reporting process and supported severity tiers.

Installation:

Easiest — one-liner via v1.2.0 release (no clone, no PowerShell):
claude --plugin-url https://github.com/daehounan/agency-agents-fork/releases/download/v1.2.0/agency-agents-fork-v1.2.0-full.zip

Or pick a scoped subset (smaller token footprint):
-engineering-finance (32 agents, 205 KB, ~1.7k description tokens)
-marketing-paid-media-sales (30 agents, 161 KB, ~1.7k tokens)
-game-development (20 agents, 144 KB, ~0.8k tokens)
Full bundle is 163 agents, 873 KB, ~8.4k description tokens (~22k at Claude runtime).

Or clone-and-install (Windows / PowerShell 7+):
git clone https://github.com/daehounan/agency-agents-fork
cd agency-agents-fork
pwsh scripts/install.ps1 -WithSkills # user-level bundle, no namespacing
pwsh scripts/install.ps1 -WithSkills -WithHooks # + hooks

Or clone-and-build a custom scope:
pwsh scripts/build-plugin.ps1 -Divisions engineering,finance,marketing
claude --plugin-dir ./dist/plugin

Uninstallation:
For release-URL installs: claude plugin disable agency-agents-fork
For user-level bundle: remove ~/.claude/agents/ and ~/.claude/skills/

Hooks: remove the entries from ~/.claude/settings.json (a .bak file from install
time is at ~/.claude/settings.json.bak- if you want to restore).

Validation: three CI workflows on every push to master — Lint Skills (24/24 pass),
audit-agent-refs (0 orphans across 180 backticked refs), and Build Plugin (asserts
163 agents + 24 skills + 2 hooks produced cleanly). All currently green; badges in
README link to each workflow. v1.2.0 release ships 4 pre-built plugin zips with
SHA256-digested artifacts.

Try it: claude --plugin-url <release-url-above> — Claude Code v2.1.143+ will load
the plugin, surface its 163 agents and 24 skills in /plugins, and (per v2.1.143
release notes) display the projected per-turn token cost.

This is a collection, not a single focused tool. The maintainer's CONTRIBUTING note
about preferring focused resources is acknowledged — if too broad, please consider
listing just the Korean/Japanese Business Navigator pair, or just the
skill-routing-arbitrator meta-skill, both of which have no public equivalent I'm
aware of.

Validate Claims

No response

Specific Task(s)

No response

Specific Prompt(s)

"Build me an Unreal Engine 5 multiplayer prototype with World Partition"
→ Routes through game-development-routing skill → suggests
Unreal Multiplayer Architect + Unreal World Builder agents in parallel.

Additional Comments

No response

Recommendation Checklist

• I have checked that this resource hasn't already been submitted
• It has been over one week since the first public commit to the repo I am recommending
• All provided links are working and publicly accessible
• I do NOT have any other open issues in this repository
• I am primarily composed of human-y stuff and not electrical circuits

[hesreallyhim]

A cooldown period is currently in effect for your account. Submitting during an active cooldown extends the restriction.

Please wait at least 14 days before opening any more submissions.

Please review the CONTRIBUTING guidelines and pinned issues before your next submission.