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.
npx agentmods add skills/rcarmo/piclaw-addons/delegatenpx skills add rcarmo/piclaw-addons --skill delegategit clone --depth 1 https://github.com/rcarmo/piclaw-addonsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rcarmo/piclaw-addons/delegate)<a href="https://agentmods.dev/skills/rcarmo/piclaw-addons/delegate"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/delegate.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00023 | $0.00980 |
| Opus 5 | $0.00012 | $0.00490 |
| Sonnet 5 | $0.00005 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
delegate scanned grade A with 0 findings 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 4d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate
Use the delegate tool for self-contained work that does not need the conversation history. The child runs with an operator-approved model, a bounded tool profile, and no persistent Pi session.
Model restriction
Delegate can use only models listed under Settings → Delegate → Approved delegate models. No providers are approved by default. The approved list requires an operator-approved provider, an ordered classified model ID, exact child-CLI executability, and no matching exclusion.
This restriction applies to automatic selection, explicit model arguments, fallback attempts, and disclosed provider response models. Delegate tool arguments and prompts cannot add models or bypass the list.
Good delegation candidates
- File, note, or code summaries
- Formatting, translation, extraction, and factual questions
- Mechanical code generation or refactoring
- Focused repository exploration and debugging
- A second-opinion review using
judge
Do not delegate when the task depends on conversation history, needs user interaction, requires frontier capability, or is simpler than describing a complete standalone prompt.
Call shape
delegate({
prompt: "Read src/client.ts. Summarize its public API in five bullets and identify compatibility risks.",
files: ["src/client.ts"],
task_category: "summarize",
tools: "read_only"
})
Categories
| Category | Target | Use for |
|---|---|---|
quick |
Tier 2 | Formatting, extraction, translation, factual Q&A |
summarize |
Tier 2 | File, note, and code summaries |
code |
Tier 3 | Code generation and refactoring |
analyze |
Tier 3 | Review, architecture, and debugging |
reason |
Tier 3 | Complex planning and multi-step logic |
judge |
Tier 3 | Critical review from another family when available |
Automatic selection is capped at the verified tier of the current model. If the current model is unknown to Delegate policy, automatic selection fails closed.
Explicit model selection
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.
- 4d ago First seen · 95 lines · 23 tokens per session scan A c083ef03bfbb
delegate is a skill published in the GitHub repository rcarmo/piclaw-addons (23 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 980 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pi
Use when needing a minimal, extensible terminal AI coding agent harness in TypeScript with plugin architecture. Pi: minimalist terminal AI coding agent emphasizing simplicity and composability.
OpenShell + Pi: build an isolated coding-agent sandbox
Use when the user wants to install, configure, migrate, harden, inspect, or troubleshoot a Pi coding agent running in NVIDIA OpenShell, especially with rootless Podman, deny-by-default networking, hidden credentials, persistent state, or A2A communication. Do not use for ordinary containerization that does not involve…
caveman
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens"…
caveman-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit.…
cavecrew
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit), or cavecrew-reviewer (diff review) instead of doing the work inline or using vanilla Explore. Subagent output is caveman-compressed so the tool-result…
caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or…