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 commands/atlanhq/atlan-python/reviewgit 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 | $0.00012 | $0.02076 |
| Opus 5 | $0.00006 | $0.01038 |
| Sonnet 5 | $0.00002 | $0.00415 |
| Haiku 4.5 | $0.00001 | $0.00208 |
Grade A, and why
review 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior code reviewer for the pyatlan SDK (Atlan Python Client). Perform a structured, high-signal code review of the current pull request. No emojis. Professional tone. Only flag issues you are confident about.
Step 1: Load repository context
Read the following files to understand the project's standards and structure. These are your evaluation criteria — do not review without them:
CLAUDE.md(if it exists — root project guidelines)pyproject.toml(project config, dependencies, tooling: ruff, mypy).github/PULL_REQUEST_TEMPLATE.md(PR checklist expectations)README.md(project overview)
Also use Glob to find any additional guideline files:
.cursor/rules/*.mdcor.cursor/*.md(coding standards, review checklists)- Any
CLAUDE.mdorBUGBOT.mdfiles in subdirectories relevant to the changed files CONTRIBUTING.mdif it exists
Subdirectory guidelines: If changed files are in subdirectories with their own guideline files, read those as well for module-specific review criteria.
Step 2: Gather PR data
Run these commands in parallel:
gh pr view --json number,title,body,state,isDraft,baseRefName,headRefName,additions,deletions,changedFiles,commits,labelsgh pr diff --name-only(list of changed files)gh pr diff(full unified diff)git log --oneline -30 $(gh pr view --json baseRefName -q .baseRefName)..HEAD(branch commit history)
Step 3: Determine review scale
Count the number of changed files from step 2.
If fewer than 100 files changed: Review all changed files directly. Read each changed file using the Read tool to understand surrounding context beyond the diff. Cache these file contents for reuse in later validation steps.
If 100 or more files changed: This is a large PR. Deploy parallel sub-agents to gather context efficiently:
- Partition changed files by top-level directory (e.g.
pyatlan/,tests/,docs/) - Launch one Explore agent per partition to read the changed files and their surrounding context
- Consolidate findings from all agents before proceeding to review passes
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 · 195 lines · 12 tokens per session scan A 2a37f4312284
review is a command published in the GitHub repository atlanhq/atlan-python (22 stars, last pushed 4d ago), licensed Apache-2.0. It adds 12 tokens to every session and 2,076 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 commands, from other repositories
weilink
Manage WeChat messaging via WeiLink — check messages, reply to contacts, download media, manage sessions.
pr-address
Address PR review comments on current branch.
enforce_standards
CRITICAL: Before running the code standards enforcer, we must prepare the stack properly and abort if there are merge conflicts.
icpg-bootstrap
Infer ReasonNodes from existing git commit history. One-time setup for existing codebases.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
run
Command "run" from ErisPulse/ErisPulse, covering erispulse.cli.commands.run 模块, 模块概述, 类列表, class reloadhandler(filesystemeventhandler) and class runcommand(command).