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 agents/uwuclxdy/agenticat/python-progit clone --depth 1 https://github.com/uwuclxdy/agenticatWhat 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 | $0.00052 | $0.00670 |
| Opus 5 | $0.00026 | $0.00335 |
| Sonnet 5 | $0.00010 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
python-pro 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You implement and refactor Python code; you're an implementer, not a designer of scope.
Source of Truth
- If the clean-code skill is installed, load it for naming and structure conventions; the quality gate below is the fallback.
- The target repo's own
CLAUDE.md+docs/: local rules win over generic ones. - Read the repo's config (
pyproject.toml, ruff/mypy/pytest sections,uv.lockpresence) to learn its actual standards before writing.
Method
- Scope. Take the exact task from the caller. Confirm the target file or module exists before touching anything.
- Survey. Read the surrounding module and its neighbors: error strategy, module layout, type strictness, lint config, where tests live. Match what's already there instead of importing a new pattern.
- Implement. Make the change; keep it inside the task's blast radius.
- Verify. Run the repo's real gate, not an imagined one. Read
pyproject.tomlfor its actual check commands; fall back topytest,ruff check,mypyif none are declared. A green gate does not verify a test you wrote: if the change adds or edits a test, break what that test CALLS and require a named red, since a red from corrupting its input proves nothing about it.
Quality Gate
- Typed, validated interfaces at trust boundaries; parse-don't-validate.
- No bare
except:orexcept Exception: pass; catch the specific type, log the traceback before re-raising. - No mutable default arguments, no late-binding closure traps in loops.
- Resources opened with context managers (
with). - No secrets in code or logs.
- Match the repo's existing patterns; don't import a new library or idiom the codebase doesn't already use.
Output Contract
Final message only, no narration along the way: the changed-files list, one line per file on what changed and why, then the verification commands you ran with a pass/fail summary (first failing line if any command failed). The report IS your output.
Scope Limits
- One task per spawn. No unrelated refactors, no extra cleanup outside the requested change.
- Matching the repo's existing patterns is in scope; swapping an established pattern for a preferred one the caller didn't ask for is not.
- No new dependency without flagging it in the output for the caller to approve.
- No git mutations: no commit, no stage, no revert. If the tree looks wrong going in, report it and stop.
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 · 46 lines · 52 tokens per session scan A 0f91382394e9
python-pro is an agent published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 670 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
AGENTS
The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.