Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add LarryStanley/pi-delegate/plugin install pi-delegateWrote 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/larrystanley/pi-delegate/doctor)<a href="https://agentmods.dev/skills/larrystanley/pi-delegate/doctor"><img src="https://agentmods.dev/badge/skills/larrystanley/pi-delegate/doctor.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 5.1 | $0.00023 | $0.00451 |
| Opus 5 | $0.00012 | $0.00226 |
| Sonnet 5 | $0.00005 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Check first:
node "${CLAUDE_PLUGIN_ROOT}/bin/pi-doctor" --check
The effective block in the output is "who a dispatch will actually reach". Having no
~/.claude/pi-delegate/config.json is normal — it means a dispatch uses the user's own pi default
model (defaultProvider / defaultModel in ~/.pi/agent/settings.json).
If problems are reported, explain each one's impact to the user before asking whether to act on it:
reasoning-missing/compat-missing— only shows up for a local OpenAI-compatible server (e.g. omlx, LM Studio, llama.cpp, vLLM): when a model is missingreasoning: trueor thecompat.chatTemplateKwargs.enable_thinkingbinding,--thinking offsilently has no effect, and the model keeps thinking without ever acting. This class can be fixed automatically.drafter-selected— the model about to be dispatched to looks like a speculative-decoding co-pilot (draft / assistant); calling it directly returns HTTP 500. Ask the user to switch to the target model; if it's a false positive, adjustdrafter_patternsin the config. This class is never auto-fixed, because which model to use is the user's decision.
Once they agree, fix whatever can be fixed automatically (a backup is made first, as models.json.pi-delegate.bak):
node "${CLAUDE_PLUGIN_ROOT}/bin/pi-doctor" --fix
--fix only adds the thinking binding to a model that is already registered and confirmed to be a
local chat-template endpoint. It never creates a provider, never inserts a model, and never touches
other models — those need values only the user knows, and a guessed configuration is harder to debug
than no configuration.
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.
- 6d ago First seen · 37 lines · 23 tokens per session scan A f8efbbc9bf7a
doctor is a skill published in the GitHub repository LarryStanley/pi-delegate (2 stars, last pushed 12d ago), licensed MIT. It adds 23 tokens to every session and 451 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 2026-08-31.
Other skills, from other repositories
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…
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
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.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.