agent-delegate

A skill for assigning work to other coding agents through PaperClip, a task-tracking system. It creates real child issues for individual agents or coordinated groups of agents.

In plain words
What is it for?
Use it when a task should be routed to a coding, infrastructure, or other specialist agent, including multi-agent projects.
Why use it?
It ensures delegated work reaches another agent as an actual assigned task instead of merely being mentioned in a comment.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/mrobinson2/azureagentforge/agent-delegate
Any agent
npx skills add mrobinson2/AzureAgentForge --skill agent-delegate
Clone the repo
git clone --depth 1 https://github.com/mrobinson2/AzureAgentForge

Made for: Claude Code, Codex.

Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,987 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00111 $0.03987
Opus 5 $0.00056 $0.01994
Sonnet 5 $0.00022 $0.00797
Haiku 4.5 $0.00011 $0.00399

Measured 2d ago against content hash 10d084dd0ba5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-delegate scanned grade A with 1 finding 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 2d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/pc-delegate.sh, scripts/test_verify_claim.py, scripts/verify_claim.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

## Use the helper, not raw curl
apps/hermes/overrides/skills/playbooks/agent-delegate/SKILL.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate or Coordinate Tasks via PaperClip Child Issues

A comment that says "I delegated this to X" is not delegation. The other agent has no way to see your comment. The only way to delegate is to create a real PaperClip issue with that agent's assigneeAgentId.

This skill covers two patterns:

  • Single-agent delegation — one parent task, one child issue, one specialist.
  • Coordination — one parent task, two or more child issues, multiple specialists.

Both patterns use the same API and the same helper script.


Runtime environment

Required environment variables

Variable Purpose
PAPERCLIP_API_KEY Bearer token for the PaperClip API (ctx.authToken for embedded Orchestrator; automation JWT for standalone Hermes)
PAPERCLIP_BASE_URL PaperClip API base URL — varies by runtime (see table below)
PAPERCLIP_ORIGIN Origin header value sent with every API request
PAPERCLIP_COMPANY_ID PaperClip company UUID (default: 00000000-0000-0000-0000-000000000000)

PAPERCLIP_API_KEY is required. If the others are unset the helper defaults apply:

  • PAPERCLIP_BASE_URLhttp://localhost:3099 (direct backend; correct for PaperClip-embedded Orchestrator)
  • PAPERCLIP_ORIGINhttp://localhost:3100
  • PAPERCLIP_COMPANY_ID00000000-0000-0000-0000-000000000000

Helper path — resolve before first use each session

The helper script lives in different locations depending on which runtime the agent is executing in. Always discover the path dynamically; never hardcode it.

DELEGATE_HELPER=""
for _p in \
  "/paperclip/.hermes/skills/playbooks/agent-delegate/scripts/pc-delegate.sh" \
  "/app/skills/playbooks/agent-delegate/scripts/pc-delegate.sh" \
  "/opt/data/skills/playbooks/agent-delegate/scripts/pc-delegate.sh"; do
  if [ -x "$_p" ]; then DELEGATE_HELPER="$_p"; break; fi
done
[ -z "$DELEGATE_HELPER" ] && { echo "ERROR: pc-delegate.sh not found in any known location" >&2; exit 2; }

Read the full file on GitHub · 372 lines

Files

What ships with it

3 files 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. 2d ago First seen · 372 lines · 111 tokens per session scan A 10d084dd0ba5

Subscribe to this mod's changes

agent-delegate is a skill published in the GitHub repository mrobinson2/AzureAgentForge (21 stars, last pushed 12d ago), licensed MIT. It adds 111 tokens to every session and 3,987 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

b00t-integration

Integration layer for b00t capabilities within opencode workflows. Provides access to b00t datum system, hive management, grok knowledge, session management, and task tracking directly from opencode.

elasticdotventures/_b00t_ · 45 tokens

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

pipeline-conductor

Operating procedure for the kirocrew-pipeline-conductor agent - run one issue/PR pipeline on one repository as a supervised fleet. Auto-pick items, stand up one worker session per item in a dedicated folder, probe them each cycle with one script call, verify claimed greens independently, intervene when a worker loops…

kirodotdev/KiroCrew · 121 tokens

coworker

Reference for the Coworker file-queue automation system: task lifecycle, directory state machine, PowerShell workers, scheduler configuration, and operational conventions. Use when you need to understand how Coworker works or debug its behavior.

platonai/Browser4 · 50 tokens

rove

Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.

Sma1lboy/rove · 56 tokens

copilot-customization

Authoritative reference for VS Code Copilot customization mechanisms: instructions, prompt files, custom agents, agent skills, MCP servers, hooks, and plugins. Use when deciding which customization type to use, creating new .instructions.md/.prompt.md/.agent.md/SKILL.md/mcp.json files from scratch, or debugging why a…

jonathan-vella/apex-accelerator · 90 tokens