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 monotykamary/pi-fabric --skill fabric-execgit clone --depth 1 https://github.com/monotykamary/pi-fabricWrote 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/monotykamary/pi-fabric/fabric-exec)<a href="https://agentmods.dev/skills/monotykamary/pi-fabric/fabric-exec"><img src="https://agentmods.dev/badge/skills/monotykamary/pi-fabric/fabric-exec/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/monotykamary/pi-fabric/fabric-exec"><img src="https://agentmods.dev/badge/skills/monotykamary/pi-fabric/fabric-exec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01240 |
| Opus 5 | $0.00023 | $0.00620 |
| Sonnet 5 | $0.00009 | $0.00248 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
fabric-exec 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fabric_exec — Python reference
Write a Python async function body in code: top-level await and return, no enclosing function or event-loop runner. Every invocation starts fresh. Only the returned JSON-compatible value reaches the model; print() goes to activity logs. Use True, False, None, native dicts/lists, and dict access for results. Never switch interpreters through shell commands to perform Fabric orchestration.
Runtime boundary
The default Python backend is Monty, a sandboxed Python subset. Arbitrary imports, third-party packages, native filesystem/network/environment access, and some Python syntax are unavailable. Use host tools for effects. import asyncio and asyncio.gather are supported. Missing native dependencies fail without fallback. Explicit CPython is trusted native code outside Schema enforce; enforce requires OS isolation and fails closed when unavailable. Neither backend exposes guest-local workflow helpers, memory visitor callbacks, or handoff predicates.
Core tools
Full code mode (also Schema enforce) exposes pi and captured extensions; orchestration-only mode leaves these on Pi's direct tool path instead.
import asyncio
manifest, matches = await asyncio.gather(
pi.read("package.json"),
pi.grep(pattern="TODO", path="src", limit=20),
)
return {"manifest": manifest, "matches": matches}
Search before bounded reads: await pi.find(pattern="*.py", path="src", limit=20), then await pi.read(path="src/main.py", offset=1, limit=80). Read continuation notices; unbounded reads cap at 2000 lines or 50KB. read, grep, find, and ls return payloads. Shell, edit, and write return dictionaries:
r = await pi.bash(command="git status --short", settle=True)
return {"ok": r["ok"], "output": r["output"], "exitCode": r.get("exitCode")}
Shell nonzero exits raise unless settle=True; timeout, cancellation, security and approval failures still raise. Shell timeout is seconds. No stdin option: write content to a file first, then use its path. Do not interpolate untrusted content into shell commands.
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.
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 Changed · -60 lines · -15 tokens per session 3634625b98c5
- 5d ago Changed 38700556e032
- 6d ago Changed · +4 lines 1b56e975e153
- 7d ago Changed cbe7584c1db1
- 12d ago First seen · 121 lines · 61 tokens per session scan A a6164af3378a
fabric-exec is a skill published in the GitHub repository monotykamary/pi-fabric (210 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,240 once invoked, about $0.0002 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
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...
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
crewai-multi-agent
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 with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
verify-samples-tool
How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.