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 kouroshez/coding-os --skill python-meta-servergit clone --depth 1 https://github.com/kouroshez/coding-osWrote 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/kouroshez/coding-os/python-meta-server)<a href="https://agentmods.dev/skills/kouroshez/coding-os/python-meta-server"><img src="https://agentmods.dev/badge/skills/kouroshez/coding-os/python-meta-server/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/kouroshez/coding-os/python-meta-server"><img src="https://agentmods.dev/badge/skills/kouroshez/coding-os/python-meta-server.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00117 | $0.01692 |
| Opus 5 | $0.00059 | $0.00846 |
| Sonnet 5 | $0.00023 | $0.00338 |
| Haiku 4.5 | $0.00012 | $0.00169 |
Grade A, and why
python-meta-server 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
python-meta-server
Purpose: Internalise the Python authoring conventions that make this meta-repo work — MCP envelope, FastMCP registration, schema migrations, extractor idempotency, hook helper structure. Without this skill, agents write Python that LOOKS correct but breaks the contracts that every consumer project depends on.
Read when: editing any of:
src/core/thinking_os/**/*.py— MCP server, tools, dispatcher, cognition.src/core/graph_os/**/*.py— backends, extractors, ingestion.src/core/board_os/**/*.py— Scrumban engine.src/core/hooks/_helpers/**/*.py— hook helpers.src/cli/**/*.py— factory CLI.src/core/web/server.py,src/core/web/routes/**/*.py— FastAPI routes.
Skip when: editing tests (*test*.py), scripts (scripts/), or one-off helpers.
Hard contracts
1. MCP envelope — Rule 13 (NON-NEGOTIABLE)
Every cos_* MCP tool returns either:
{"ok": True, "data": <payload>, "meta": {"layer": "<layer>", ...}}
{"ok": False, "error": {"category": "<cat>", "message": "<human>", "retryable": <bool>}}
Use @safe_tool from src/core/thinking_os/tools/_shared.py:
from thinking_os.tools._shared import safe_tool, ok, fail
@safe_tool
@mcp.tool()
def cos_my_tool(arg: str) -> dict:
"""One-line description for FastMCP.""" # ← Rule 12
if not arg:
return fail("validation", "arg must be non-empty")
return ok({"result": ...}, meta={"layer": "thinking_os"})
Categories: validation · not_found · unavailable (retryable) · conflict (retryable) · internal.
2. Docstrings — Rule 12
ONE-line docstring on @mcp.tool functions only — FastMCP exposes
that line as the agent-facing description. NO multi-line docstrings on
internal helpers. Comments by exception, not by default.
3. Schema migrations — Rule 9
Adding a persistent table: write src/core/thinking_os/migrations/vN+1_<name>.sql.
NEVER edit a previous migration. tests/test_db.py guards the invariant.
4. Extractor idempotency
What ships with it
2 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.
- 5d ago First seen · 163 lines · 117 tokens per session scan A 02d9b5d98675
python-meta-server is a skill published in the GitHub repository kouroshez/coding-os (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 117 tokens to every session and 1,692 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
fastapi-patterns
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.
python-patterns
Python-specific design patterns and best practices including protocols, dataclasses, context managers, decorators, async/await, type hints, and package organization. Use when working with Python code to apply Pythonic patterns.
python-testing
Python testing best practices using pytest including fixtures, parametrization, mocking, coverage analysis, async testing, and test organization. Use when writing or improving Python tests.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.