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 skills add baldaworks/callee --skill run-agentgit clone --depth 1 https://github.com/baldaworks/calleeWrote 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/baldaworks/callee/run-agent)<a href="https://agentmods.dev/skills/baldaworks/callee/run-agent"><img src="https://agentmods.dev/badge/skills/baldaworks/callee/run-agent.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 | $0.00041 | $0.01619 |
| Opus 5 | $0.00020 | $0.00809 |
| Sonnet 5 | $0.00008 | $0.00324 |
| Haiku 4.5 | $0.00004 | $0.00162 |
Grade A, and why
run-agent 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 7d 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.
This is a copy
100% identical to callee-run-agent — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Callee agents
Use callee when available. Otherwise use the pinned fallback npx --yes @baldaworks/[email protected] for every command in the task.
Discover and select
For each fresh task, inspect the versioned catalog:
callee agent list --json
Resolve a naturally named agent against its exact agent ID or unambiguous description. Inspect the selected tree and every required parameter before execution:
callee agent view "<agent-id>" --json
The selected ID may identify a Role, Script, Human, Sequential, Loop, or Router. Treat all kinds as the same run boundary. Do not invent a separate workflow command.
Select the execution path
Inspect the authored tree first with agent view --json. Preserve its
permission policy unless the user explicitly requests an override. When using
--permissions, inspect the effective projection with the same override before
running:
callee --permissions="<ask|allow|deny>" agent view "<agent-id>" --json
Read top-level specDrivenInteractive as the authored baseline and top-level
interactive as the effective whole-run mode after the permission override.
For every Role, inspect authoredInteractive, effective interactive,
authoredPermissions, and effective permissions. Keep permissions and the
Role protocol independent.
Choose the host execution path from this matrix. Apply an explicit
--interactive row first; otherwise use the effective tree rows:
| Condition | Whole-run mode and Role protocol | Host path |
|---|---|---|
One-shot Roles with effective ask, no Human |
Interactive run; Roles remain one-shot | Controlling PTY |
One-shot Roles with effective allow or deny, no Human |
Non-interactive run | Direct, without a PTY |
| Any effective interactive Role or any Human | Interactive run | Controlling PTY |
Explicit --interactive=true with any permission mode |
Interactive run; every Role uses REPL | Controlling PTY |
Explicit --interactive=false with effective allow or deny |
Non-interactive run; every Role is one-shot | Direct after preflight |
What ships with it
1 file 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.
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.
- 7d ago First seen · 132 lines · 41 tokens per session scan A 8a1a7da136cb
run-agent is a skill published in the GitHub repository baldaworks/callee (74 stars, last pushed 27d ago), licensed MIT. It adds 41 tokens to every session and 1,619 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to callee-run-agent, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
research-crewai
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration wi...
research-dspy
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming.
research-autogpt
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automa...
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
haiku
When writing a haiku for this bot, follow these conventions.
typescript-providers
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.