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 agentmods add skills/atlanhq/atlan-python/releasenpx skills add atlanhq/atlan-python --skill releasegit clone --depth 1 https://github.com/atlanhq/atlan-pythonWhat 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 | $0.00021 | $0.01168 |
| Opus 5 | $0.00010 | $0.00584 |
| Sonnet 5 | $0.00004 | $0.00234 |
| Haiku 4.5 | $0.00002 | $0.00117 |
Grade A, and why
release 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 yesterday.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create SDK Release
Bumps the SDK version, generates release notes in HISTORY.md, and commits on a dedicated release branch.
Usage
/release patch— bump patch version (e.g., 9.2.1 → 9.2.2)/release minor— bump minor version (e.g., 9.2.1 → 9.3.0)/release major— bump major version (e.g., 9.2.1 → 10.0.0)/release 9.3.0— set an explicit version
If no argument is provided, default to patch.
Instructions
1. Determine the new version
Read the current version from pyatlan/version.txt. Parse the argument to compute the new version:
patch: increment the third number, e.g.,9.2.1→9.2.2minor: increment the second number, reset patch, e.g.,9.2.1→9.3.0major: increment the first number, reset minor and patch, e.g.,9.2.1→10.0.0- If the argument matches a semver pattern (e.g.,
9.3.0), use it directly
Confirm the new version with the user before proceeding.
2. Gather changes since last release
Always gather from origin/main — that's where PRs are merged. The current working branch is irrelevant here.
Step 1 — find the last release commit on main and list everything since it:
git fetch origin main --quiet
git log --oneline $(git log --oneline origin/main | grep "\[release\]" | head -1 | awk '{print $1}')..origin/main
Step 2 — extract PR numbers from merge commits and fetch details for each:
git log --oneline $(git log --oneline origin/main | grep "\[release\]" | head -1 | awk '{print $1}')..origin/main | grep "Merge pull request" | grep -oE '#[0-9]+' | tr -d '#'
Then for each PR number, run:
gh pr view <number> --json title,labels,body,mergedAt
If gh is not authenticated, fall back to the commit subjects alone — do NOT skip this step or silently use an empty list. Note any PRs you couldn't fetch so the user knows the notes may be incomplete.
Step 3 — also run this to catch non-merge commits (direct pushes, fixups, etc.):
git log --oneline --no-merges $(git log --oneline origin/main | grep "\[release\]" | head -1 | awk '{print $1}')..origin/main
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.
- yesterday First seen · 145 lines · 21 tokens per session scan A e9fe52e5deae
release is a skill published in the GitHub repository atlanhq/atlan-python (22 stars, last pushed 4d ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,168 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 2026-08-30.
Other skills, from other repositories
notebooklm
Complete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X".
vulners-api-python-sdk
Use when modifying, testing, documenting, or reviewing the Vulners Python SDK. Covers the v4 architecture (typed sync/async clients, resource namespaces, bulletin model hierarchy, unasync codegen), the preserved legacy v3 surface, uv-based tooling, the 100% branch-coverage gate, safe API-key handling, and defensive…
zapier-sdk
Zapier SDK for TypeScript. Programmatic access to 9,000+ apps on a user's behalf via Zapier's OAuth and audit layer. Use when writing code that needs to run actions in third-party apps (send an email, upsert a CRM record, look up a spreadsheet row, post to a chat) without managing per-app OAuth or vendor SDKs.…
servicenow-sdk-docs-builder
Automation skill to generate or update the servicenow-sdk-docs documentation skill by fetching and processing the ServiceNow SDK and Examples repositories. It combines READMEs, extracts code samples, harvests the SDK CLI/auth docs, and creates a self-contained, portable documentation skill.
servicenow-sdk-docs
A comprehensive, self-contained collection of ServiceNow SDK (Fluent API) examples and core documentation. Use this when the agent needs to reference how to use the ServiceNow SDK for various components like Tables, REST APIs, UI Actions, Script Includes, etc. All source code is bundled within the skill for…
writing-python-code
Enforces Python 3.14 code style, logging rules, type annotations, design patterns, testing strategy, and clean code principles for the appkit project. Use when writing, reviewing, or refactoring Python code, creating new modules, or adding tests.