Agent skill

Cross Agent Delegation

Cross-agent task routing — Codex auto-review, Kimi delegation by complexity score (iCPG + Claude reasoning), iCPG + Mnemos mandatory for all agents

MITAuto-check passed

Install Cross Agent Delegation

skills CLI

$ npx skills add alinaqi/maggy --skill cross-agent-delegation -a claude-code

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

GitHub CLI

$ gh skill install alinaqi/maggy cross-agent-delegation --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/alinaqi/maggy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cross-agent-delegation .claude/skills/cross-agent-delegation && 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/

Paste into Claude Code

Install the "cross-agent-delegation" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/cross-agent-delegation into .claude/skills/cross-agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-delegation", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/alinaqi/maggy/tree/main/skills/cross-agent-delegation

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add alinaqi/maggy --skill cross-agent-delegation -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install alinaqi/maggy cross-agent-delegation --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cross-agent-delegation .agents/skills/cross-agent-delegation && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "cross-agent-delegation" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/cross-agent-delegation into .agents/skills/cross-agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-delegation", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alinaqi/maggy --skill cross-agent-delegation -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install alinaqi/maggy cross-agent-delegation --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cross-agent-delegation .cursor/skills/cross-agent-delegation && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "cross-agent-delegation" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/cross-agent-delegation into .cursor/skills/cross-agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-delegation", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/alinaqi/maggy.git --path skills/cross-agent-delegation

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add alinaqi/maggy --skill cross-agent-delegation -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install alinaqi/maggy cross-agent-delegation --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cross-agent-delegation .gemini/skills/cross-agent-delegation && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "cross-agent-delegation" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/cross-agent-delegation into .gemini/skills/cross-agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-delegation", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install alinaqi/maggy cross-agent-delegation

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add alinaqi/maggy --skill cross-agent-delegation -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cross-agent-delegation .github/skills/cross-agent-delegation && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "cross-agent-delegation" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/cross-agent-delegation into .github/skills/cross-agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-delegation", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alinaqi/maggy --skill cross-agent-delegation -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install alinaqi/maggy cross-agent-delegation --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cross-agent-delegation .opencode/skills/cross-agent-delegation && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "cross-agent-delegation" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/cross-agent-delegation into .opencode/skills/cross-agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-delegation", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: cross-agent-delegation
GitHub stars: 707
Token cost: ~1.9k tokens
SKILL.md length: 509 words
Files: 1
Skills in repo: 71
Repo updated: Sep 24, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Cross-agent task routing — Codex auto-review, Kimi delegation by complexity score (iCPG + Claude reasoning), iCPG + Mnemos mandatory for all agents

Works in 5 steps: Score complexity, not file count → Sum → routing → Floor — trivial-case shortcut → …
SKILL.md covers Tool Detection, Codex Auto-Review (Stop Hook —…, Kimi Delegation (Claude… and iCPG — Mandatory for All Agents, plus 2 more sections
Calls git

What it does

Cross Agent Delegation is an agent skill from alinaqi/maggy. Cross-agent task routing — Codex auto-review, Kimi delegation by complexity score (iCPG + Claude reasoning), iCPG + Mnemos mandatory for all agents

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Kimi. The repository describes itself as: What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center. The licence is MIT.

Example prompts

“/cross-agent-delegation”

Workflow steps

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

Score complexity, not file count
Sum → routing
Floor — trivial-case shortcut
Delegate via Bash
Read Results

What it can do on your machine

Read from SKILL.md and the folder at commit 72a456e. 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
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

Cross Agent Delegation loads about 1.9k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 509 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~43
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k

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 alinaqi/maggy at commit 72a456e, republished under its MIT licence (© alinaqi). 509 words, ~1,882 tokens.

Download SKILL.mdSave it as .claude/skills/cross-agent-delegation/SKILL.md (or your agent's skills folder).

name: cross-agent-delegation
description: Cross-agent task routing — Codex auto-review, Kimi delegation by complexity score (iCPG + Claude reasoning), iCPG + Mnemos mandatory for all agents
when-to-use: Always loaded when multiple AI CLI tools are available (Claude, Kimi, Codex)
user-invocable: false
effort: medium

Cross-Agent Delegation

Claude Code orchestrates task routing to Kimi and Codex. The user interacts with Claude only — delegation happens behind the scenes.

Tool Detection

At session start, detect available tools:

bash

command -v kimi &>/dev/null && HAS_KIMI=true || HAS_KIMI=false
command -v codex &>/dev/null && HAS_CODEX=true || HAS_CODEX=false

Codex Auto-Review (Stop Hook — Automatic)

When Codex is installed, a Stop hook reviews code after tests pass:

TDD loop check runs tests
codex-auto-review.sh runs Codex on the diff
Critical/High findings feed back to Claude (exit 2)
Clean reviews pass through (exit 0)

Fully automatic. No user or Claude action needed.

Kimi Delegation (Claude Orchestrates)

When Kimi is installed and the task complexity is bounded, Claude delegates directly — the user does not need to run anything.

Step 1: Score complexity, not file count

File count is a poor proxy for delegation risk. A 1-file change to an authz path is harder than a 12-file rename. Score the task on five dimensions, each 0-2, sourced from iCPG signals plus Claude's semantic reasoning:

Dimension	0 (low)	1 (medium)	2 (high)	Source
Cyclomatic / surface depth	<10 LOC, no branches	10-50 LOC, ≤3 branches	50+ LOC or nested control flow	iCPG `query_graph` over function bodies
Fan-out (consumer blast radius)	0-2 callers	3-10 callers	11+ callers	iCPG `trace_path(<symbol>, mode=callers)`
Crosses a security boundary (SEC-006, auth, PII, RLS, org-scope, billing, payments)	None	Tangential	Direct read or write	iCPG SEC-* / R-063 tags + grep for `org_id`, `user_id`, `auth`, `pii`
Concurrency / transactional	Pure / sync	Async only	Locks, transactions, atomic claims, `FOR UPDATE`, `asyncio.Lock`, `session.begin`	iCPG concurrency flags + grep
Domain invariants required	None / well-documented inline	Some implicit (need to read 1-2 files)	Heavy (cross-doc, ADR-bound, RFC-bound)	Claude reasoning + iCPG ADR linkage

bash

# Auto-collect signals
icpg query blast <scope> --format json    # fan-out, async flags, sec tags
grep -rE "org_id|user_id|auth|pii"  <file>  # cheap sec heuristic if iCPG flags absent
grep -rE "asyncio.Lock|FOR UPDATE|session.begin" <file>  # concurrency heuristic

Step 2: Sum → routing

Total score	Route	Rationale
0-3	Kimi solo	Bounded surface, no security/concurrency/cross-doc concerns
4-6	Kimi → Codex auto-review (no user prompt)	Real risk, but not so high that we need full Claude context — Codex catches what Kimi might miss
7-10	Claude handles directly	Cross-cutting / security-critical / concurrency-heavy — needs full context

Show full SKILL.md (194 more words)Show less

Step 3: Floor — trivial-case shortcut

To skip iCPG-query cost on truly trivial work:

bash

# If <2 files changed AND no SEC/auth/PII/concurrency keyword in diff,
# → auto-Kimi without scoring.
FILES=$(git diff --name-only | wc -l)
HAS_RISK_KEYWORDS=$(git diff | grep -ciE "org_id|auth|pii|asyncio|FOR UPDATE|transaction|session\.begin" || true)
if [ "$FILES" -lt 2 ] && [ "$HAS_RISK_KEYWORDS" -eq 0 ]; then
  AUTO_KIMI=true
fi

This handles the trivial-rename / typo-fix case without paying the iCPG round-trip.

When NOT to Delegate (overrides scoring)

User explicitly asked Claude to do it
Cross-service changes (API + frontend + database) — needs full context regardless of score
Production hotfix on a release branch — cross-tool review latency is too high
Score 7+ in any single dimension (one critical axis is enough to keep Claude in the loop)

Step 4: Delegate via Bash

Claude writes a mnemos checkpoint, then runs Kimi headless:

bash

# 1. Save current context to disk
mnemos checkpoint --force

# 2. Get context summary for Kimi
CONTEXT=$(mnemos resume 2>/dev/null)

# 3. Get constraints for target files
CONSTRAINTS=$(icpg query constraints <target-file> 2>/dev/null)

# 4. Run Kimi headless with full context
kimi --print -y -w . -p "
## Context (from mnemos checkpoint)
$CONTEXT

## Constraints (from iCPG)
$CONSTRAINTS

## Task
<specific task description>

## Rules
- Run tests after changes
- Record changes: icpg record --base main
- Write checkpoint when done: mnemos checkpoint --force
"

Step 4: Read Results

After Kimi finishes, Claude:

bash

# Read what Kimi did
mnemos resume          # Kimi's checkpoint
icpg status            # Kimi's recorded symbols
git diff               # Kimi's file changes

When NOT to Delegate

Security-sensitive code (auth, crypto, payments)
Cross-service changes (API + frontend + database)
Refactors that touch shared interfaces
User explicitly asked Claude to do it

iCPG — Mandatory for All Agents

Before ANY code change, Claude runs these (and includes results when delegating):

Pre-Task Queries

bash

# 1. Duplicate check — already done?
icpg query prior "<goal>"

# 2. Constraints — what invariants apply?
icpg query constraints <file-path>

# 3. Risk — is this symbol fragile?
icpg query risk <symbol-name>

After Code Changes

bash

icpg record --reason <id> --base main
icpg drift check

Mnemos — Mandatory for All Agents

At Task Start

bash

mnemos add goal "<task description>"

At Sub-Goal Boundaries

bash

mnemos checkpoint

At Task End (auto-handled by Stop hook)

bash

mnemos checkpoint --force

Context Transfer Between Tools

The checkpoint is the bridge. Claude writes it, Kimi reads it:

bash

# Claude saves state
mnemos checkpoint --force

# Kimi (or Codex) reads state
mnemos resume

The checkpoint contains: goal, constraints, recent files, git state, fatigue level.

Full Orchestration Flow

TASK ARRIVES (user tells Claude)
    |
    v
[1] Claude: icpg query prior "<goal>"     ← Already done?
[2] Claude: trivial-case shortcut         ← <2 files & no risk keywords?
    |
    +-- YES + Kimi installed -----> AUTO-KIMI (no scoring)
    |
    +-- NO ↓
    v
[3] Claude: score complexity (5 dims × 0-2, iCPG + reasoning)
    |
    +-- score 0-3   ----> KIMI SOLO PATH
    |   [a] mnemos checkpoint --force
    |   [b] kimi --print -y -p "..."
    |   [c] mnemos resume + git diff
    |   [d] Continue in Claude
    |
    +-- score 4-6   ----> KIMI + CODEX REVIEW PATH
    |   [a] mnemos checkpoint --force
    |   [b] kimi --print -y -p "..."
    |   [c] codex review --uncommitted    ← Auto-review the diff
    |   [d] If P0/P1 findings: re-prompt Kimi with findings
    |   [e] Once clean: continue in Claude
    |
    +-- score 7-10  ----> CLAUDE DIRECT PATH (full context)
    |
    v
[4] icpg query constraints <files>         ← Invariants
[5] icpg query risk <symbols>              ← Fragility
[6] mnemos add goal "<task>"               ← Track in memory
    |
    v
[7] IMPLEMENT (TDD: RED -> GREEN)
    |
    v
[8]  Stop: tdd-loop-check.sh               ← Tests pass?
[9]  Stop: codex-auto-review.sh            ← Codex reviews diff
[10] Stop: icpg-stop-record.sh             ← Record symbols
[11] Stop: mnemos-checkpoint.sh            ← Save memory

Files

Just SKILL.md in skills/cross-agent-delegation of alinaqi/maggy.

Open the folder on GitHubat commit 72a456e

Compare with similar skills

Cross Agent Delegation 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.

Cross Agent Delegation compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Cross Agent Delegation this skillalinaqi/maggy	707	—	~1.9k	Automated safety check: Pass	MIT	17 days ago
CCS Task Delegationkaitranntt/ccs	2.9k	—	~1.8k	Automated safety check: Pass	MIT	10 days ago
Ccmanager Configkbwo/ccmanager	1.3k	—	~1.5k	Automated safety check: Pass	MIT	yesterday
Kimi WebbridgeMoonshotAI/kimi-code	7.8k	—	~3.6k	Automated safety check: Pass	MIT	today
Open Kimi Pptjinwyp/open-ppt-skill	161	2 repos	~5.1k	Automated safety check: Pass	MIT	2 mo ago
Helmor Bump Vendorsdohooo/helmor	1.3k	—	~2.1k	Automated safety check: Pass	Apache-2.0	1 mo ago

Similar skills

CCS Task Delegation
kaitranntt/ccs
Hands simple, deterministic tasks such as typo fixes, tests and small refactors to cheaper models through the ccs CLI, choosing a profile from your config.
2.9k GitHub stars~1.8k tokensUpdated 10 days ago
Agent WorkflowsAuto-check passed
Ccmanager Config
kbwo/ccmanager
Set up, review, or repair a CCManager config — .ccmanager.json at a git repository root, or the global ~/.config/ccmanager/config.json.
1.3k GitHub stars~1.5k tokensUpdated yesterday
DevelopmentAuto-check passed
Kimi Webbridge
MoonshotAI/kimi-code
Kimi Browser Extension（Kimi 浏览器扩展，原 Kimi WebBridge）lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login…
7.8k GitHub stars~3.6k tokensUpdated today
DevelopmentAuto-check passed
Open Kimi Ppt
jinwyp/open-ppt-skill
Create, edit, replicate, read, and export presentations. An agent skill from jinwyp/open-ppt-skill.
161 GitHub starsUsed in 2 repos~5.1k tokens
Documents & OfficeAuto-check passed
Helmor Bump Vendors
dohooo/helmor
Bump or upgrade the pinned versions of Helmor's bundled agent CLIs, SDKs, and supporting binaries — Claude Code + claude-agent-sdk (lockstep), Codex, Cursor SDK, OpenCode, Kimi, Pi, and gh / glab /…
1.3k GitHub stars~2.1k tokensUpdated 1 mo ago
Agent WorkflowsAuto-check passed
Gen Changesets
MoonshotAI/kimi-code
A skill your agent uses when generating changesets in the kimi-code repository — deciding whether to write one, which package to list, the bump level, the wording, and the confirmation workflow.
7.8k GitHub stars~1.1k tokensUpdated today
DevelopmentAuto-check passed

Questions about Cross Agent Delegation

What does Cross Agent Delegation do?

Cross-agent task routing — Codex auto-review, Kimi delegation by complexity score (iCPG + Claude reasoning), iCPG + Mnemos mandatory for all agents. Cross Agent Delegation is an agent skill from alinaqi/maggy.

How do I install Cross Agent Delegation in Claude Code?

Run `npx skills add alinaqi/maggy --skill cross-agent-delegation -a claude-code`. Or copy the skill folder (skills/cross-agent-delegation in alinaqi/maggy) into .claude/skills/cross-agent-delegation in your project. Claude Code loads it when a task matches its description.

How do I install Cross Agent Delegation in Codex?

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

Can I use Cross Agent Delegation 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 alinaqi/maggy --skill cross-agent-delegation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cross-agent-delegation, .gemini/skills/cross-agent-delegation, .github/skills/cross-agent-delegation and .opencode/skills/cross-agent-delegation in your project.

What does Cross Agent Delegation need to run?

Going by SKILL.md and its folder, Cross Agent Delegation needs the command-line tools its instructions call (git).

Does Cross Agent Delegation 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 Cross Agent Delegation 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 Cross Agent Delegation use?

Cross Agent Delegation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cross Agent Delegation use?

About 1.9k tokens (SKILL.md is roughly 7.5k 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 Cross Agent Delegation?

Skills that share tags, products or a category with Cross Agent Delegation: CCS Task Delegation (kaitranntt/ccs, 2.9k stars), Ccmanager Config (kbwo/ccmanager, 1.3k stars), Kimi Webbridge (MoonshotAI/kimi-code, 7.8k stars) and Open Kimi Ppt (jinwyp/open-ppt-skill, 161 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cross Agent Delegation?

alinaqi (a GitHub user) maintains it in alinaqi/maggy, which has 707 GitHub stars. The repository holds 71 skills in this directory. The repository was last updated on September 24, 2026.

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

Install Cross Agent Delegation

Facts

At a glance

What it does

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Cross-Agent Delegation

Tool Detection

Codex Auto-Review (Stop Hook — Automatic)

Kimi Delegation (Claude Orchestrates)

Step 1: Score complexity, not file count

Step 2: Sum → routing

Step 3: Floor — trivial-case shortcut

When NOT to Delegate (overrides scoring)

Step 4: Delegate via Bash

Step 4: Read Results

When NOT to Delegate

iCPG — Mandatory for All Agents

Pre-Task Queries

After Code Changes

Mnemos — Mandatory for All Agents

At Task Start

At Sub-Goal Boundaries

At Task End (auto-handled by Stop hook)

Context Transfer Between Tools

Full Orchestration Flow

Files

Compare with similar skills

Similar skills

More from alinaqi/maggy

Related

Questions about Cross Agent Delegation