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/johnnichev/selectools/featurenpx skills add johnnichev/selectools --skill featuregit clone --depth 1 https://github.com/johnnichev/selectoolsWhat 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 | $0.00020 | $0.01550 |
| Opus 5 | $0.00010 | $0.00775 |
| Sonnet 5 | $0.00004 | $0.00310 |
| Haiku 4.5 | $0.00002 | $0.00155 |
Grade A, and why
feature 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 2d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Implementation
Implement the following feature: $ARGUMENTS
Live Project State
- Version: !
grep -m1 __version__ src/selectools/__init__.py - Tests: !
pytest tests/ --collect-only -q 2>/dev/null | tail -1 - Last example: !
ls examples/*.py | tail -1 - Next example number: use the next zero-padded number after the last one above
- StepTypes: !
python3 -c "from selectools.trace import StepType; print(len(StepType))" 2>/dev/null - Observer events: !
python3 -c "from selectools.observer import AgentObserver; import inspect; print(len([m for m in dir(AgentObserver) if m.startswith('on_')]))" 2>/dev/null
1. Cross-Feature Impact Analysis
Before writing code, determine:
- Does this touch
agent/core.py? If so, follow the execution flow:_prepare_run → cancellation check → budget check → model selection → on_iteration_start → provider call → _process_response → guardrails → parser → policy → coherence → tool execution → post-tool cancellation check → on_iteration_end - Does
AgentConfiginagent/config.pyneed new fields? - Does
__init__.pyneed new public exports? - Does
trace.pyneed newStepTypevalues? (currently 16) - Does
observer.pyneed new events? If so, add to ALL FOUR classes:AgentObserver(no-op default)AsyncAgentObserver(async no-op)LoggingObserver(JSON emission via_emit())SimpleStepObserver(delegate toself._cb())
- Does
AgentResultneed new fields? - Update
tests/test_phase1_design_patterns.pyStepType count if adding new types
2. Write Source Code
New module pattern:
"""Module docstring — one line."""
from __future__ import annotations
from dataclasses import dataclass
from typing import Any, Dict, List, Optional
# Lazy imports for optional deps
try:
import some_lib
except ImportError:
some_lib = None # type: ignore[assignment]
For agent loop changes — add to the shared helpers (_check_budget, _build_cancelled_result, etc.) rather than duplicating in run()/arun()/astream(). Use _RunContext to carry per-run state.
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.
- 2d ago First seen · 157 lines · 20 tokens per session scan A 449a00be7ec7
feature is a skill published in the GitHub repository johnnichev/selectools (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,550 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
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
Content Safety & Filtering
Topic-based content filtering to block harmful or unauthorized content in agent output.
guardrails-docs-access
Access and read guardrails skill documentation, configuration examples, and usage guides at runtime.
Output Security & Secret Scanning
Prevent sensitive data (secrets, credentials, PII) from leaking in agent output.
Policy Configuration Hierarchy
How guardrail policies cascade from organization through team to project level.
Sandbox Isolation
Run untrusted or risky commands in Docker-based sandbox with resource limits and network isolation.