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/larrystanley/pi-delegate/setupnpx skills add LarryStanley/pi-delegate --skill setupgit clone --depth 1 https://github.com/LarryStanley/pi-delegateWhat 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 | $0.00041 | $0.02595 |
| Opus 5 | $0.00020 | $0.01298 |
| Sonnet 5 | $0.00008 | $0.00519 |
| Haiku 4.5 | $0.00004 | $0.00260 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Ask first.** This one writes to `~/.claude/settings.json`, which is the user's own global How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-delegate setup
This is a guided walkthrough for the person setting up pi-delegate, not a script to run unattended. Work through the steps below in order. Report each check's result in plain language before moving on. Wherever a step says ask, stop and wait for the user's answer — do not barrel through to the next step on your own judgment.
1. Detect
Check whether pi is on PATH:
command -v pi
If this prints nothing, pi is not installed and nothing else in this plugin can work yet.
Tell the user:
- Install it with
npm install -g @earendil-works/pi-coding-agent(https://www.npmjs.com/package/@earendil-works/pi-coding-agent) - pi-delegate also needs Node ≥ 22.
Then stop here — do not continue to step 2 until command -v pi finds it.
If pi is found, check its version and run the environment check:
pi --version
node "${CLAUDE_PLUGIN_ROOT}/bin/pi-doctor" --check
Read the effective block in the JSON output — that's who a dispatch will actually reach.
Report it to the user plainly: which provider and model dispatches will use, and where that
came from (source is either pi-delegate config.json or pi settings.json).
- This plugin emits no
--provider/--modelflags by default. A dispatch simply inherits whateverpiitself is already pointed at — anthropic, openai, a local OpenAI-compatible server. There is no requirement to run a local inference server; whatever the user already uses withpiinteractively is what dispatches will use too. - If
effective.providerandeffective.modelare both empty, pi has nodefaultProvider/defaultModelset in~/.pi/agent/settings.json, and pi-delegate has no~/.claude/pi-delegate/config.jsonpinning one either. In that case dispatches will land on whatever pi's own resolver picks (the first model with a usable API key) — tell the user this is usually not what they want, and that configuring a provider forpiitself is outside this plugin's scope: runpiinteractively once and complete its own provider setup, or setdefaultProvider/defaultModeldirectly in~/.pi/agent/settings.json. Then re-run the check above before continuing. - Note the
problemsarray (if any) but don't act on it yet — that's step 3.
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.
- yesterday First seen · 204 lines · 41 tokens per session scan B 9e22d8aeb0a1
setup is a skill published in the GitHub repository LarryStanley/pi-delegate (2 stars, last pushed 8d ago), licensed MIT. It adds 41 tokens to every session and 2,595 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
reduce-foreground-guard-prompts
Explain why foreground-guard is prompting on Bash commands and how to stop the avoidable prompts. Use when the user asks "why am I getting so many foreground-guard prompts", "reduce foreground-guard prompts", "stop the watch/sleep/gh run watch permission prompts", or otherwise wants fewer confirmation prompts from…
reduce-workspace-guard-prompts
Explain why workspace-guard is prompting on Bash file commands and how to stop the avoidable prompts. Use when the user asks "why am I getting so many permission prompts", "reduce workspace-guard prompts", "stop the grep/cat permission prompts", or otherwise wants fewer confirmation prompts from this hook.
hs
ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ. Check curl, wget, rm, sudo, apt, dpkg, chmod, dd, format, powershell, bash, sh. Check pipe patterns like | sh or | bash. Check shell wrappers like bash -c, xargs, find -exec. Check cloud CLI (aws, gcloud, kubectl, terraform). Check when user says sysadmin told…
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
evolve
Start or monitor an evolutionary development loop.