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-schemagit 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-schema)<a href="https://agentmods.dev/skills/monotykamary/pi-fabric/fabric-schema"><img src="https://agentmods.dev/badge/skills/monotykamary/pi-fabric/fabric-schema/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-schema"><img src="https://agentmods.dev/badge/skills/monotykamary/pi-fabric/fabric-schema.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 | $0.00037 | $0.00908 |
| Opus 5 | $0.00018 | $0.00454 |
| Sonnet 5 | $0.00007 | $0.00182 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
fabric-schema 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 5d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabric Schema — Python
Start with await schema.status(). off leaves state discipline optional; audit reports would-block events without changing authorization; enforce permits protected changes only through one same-fabric_exec hypothesis → verification → commit. Direct mutations, agents, state/mesh writes, compaction, MCP, extensions, and external providers are blocked. Evidence is not proof of general semantic correctness.
Adapt the literal edit, project-relative path, and host-configured trusted-command name to the observed task. Read source first; never invent command shell text or arguments.
await pi.read(path="src/parser.ts")
hypothesis = await schema.hypothesize(label="parser-local-form", summary="The declared parser edit accepts the local form while focused checks remain green", evidence=[
{"kind": "file_contains", "path": "src/parser.ts", "literal": "old literal"},
{"kind": "trusted_command", "name": "parser-focused-tests"},
])
verification = await schema.verify(hypothesisId=hypothesis["hypothesisId"])
safe_verification = {key: value for key, value in verification.items() if key != "certificate"}
certificate = verification.get("certificate")
if not verification["verified"] or not certificate:
if certificate:
await schema.abort(hypothesisId=hypothesis["hypothesisId"], certificate=certificate)
return {"status": "failed", "verification": safe_verification}
observed = None
for result in verification["results"]:
if result["evidence"].get("path") == "src/parser.ts" and result.get("observedSha256"):
observed = result["observedSha256"]
break
if not observed:
await schema.abort(hypothesisId=hypothesis["hypothesisId"], certificate=certificate)
return {"status": "failed", "reason": "missing observed SHA-256", "verification": safe_verification}
commit = await schema.commit(hypothesisId=hypothesis["hypothesisId"], certificate=certificate, operations=[
{"kind": "edit", "path": "src/parser.ts", "oldText": "old literal", "newText": "new literal", "expectedSha256": observed}
], postconditions=[
{"kind": "file_contains", "path": "src/parser.ts", "literal": "new literal"},
{"kind": "trusted_command", "name": "parser-focused-tests"},
])
return {"status": "success" if commit["outcome"] == "committed" else "failed", "commit": commit}
The certificate is single-use, invocation-bound, short-lived, and bound to the workspace fingerprint, hypothesis and generation. Never return it for later use. If stopping after successful verification, call await schema.abort(hypothesisId=hypothesis["hypothesisId"], certificate=certificate) in the same invocation. Missing, stale, failed, timed-out, cancelled, or workspace-changing evidence voids the plan.
Operations are local regular files: edit/delete require expectedSha256; writes require expected={"absent": True} or expected={"sha256": observed}. Path/symlink escape is rejected. Only committed is success; preserve rollback and quarantine details. Evidence forms are file_exists, file_absent, file_contains (literal), file_sha256, and trusted_command. Remote effects are not transactional. complexityReduction=True also needs scoped behavior-preservation postconditions; it is not an objective complexity measurement.
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.
- 5d ago Changed · -66 lines 7eb2eafeebc2
- 12d ago First seen · 122 lines · 37 tokens per session scan A 819118cb839e
fabric-schema is a skill published in the GitHub repository monotykamary/pi-fabric (213 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 908 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.