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/nrdxp/predicate/pythonnpx skills add nrdxp/predicate --skill pythongit clone --depth 1 https://github.com/nrdxp/predicateWhat 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 | $0.00110 | $0.04418 |
| Opus 5 | $0.00055 | $0.02209 |
| Sonnet 5 | $0.00022 | $0.00884 |
| Haiku 4.5 | $0.00011 | $0.00442 |
Grade A, and why
python 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 — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Language Idioms
Work with the language. Lean into duck typing, generators, context managers, and the standard library. Write code that reads like pseudocode — if it needs a comment to explain what it does, rewrite it.
Core Philosophy
- Readability is a feature — code is read far more than it is written; optimize for the reader
- Explicit over implicit — no magic, no hidden state, no clever tricks
- Flat over nested — avoid deep indentation; early returns, guard clauses, comprehensions
- Composition over inheritance — functions, protocols, and dataclasses beat class hierarchies
- Standard library first — reach for builtins and
stdlibbefore adding dependencies
Formatting
Let the formatter handle it. Pick one formatter project-wide and enforce it in CI.
ruff check . # Lint
ruff format . # Format
black . # Alternative formatter
Non-Negotiables
| Rule | Standard |
|---|---|
| Indentation | 4 spaces. Tabs are prohibited. |
| Operator spacing | x = y * 12 + 13, not x=y*12+13 |
| Quote style | Pick single or double project-wide; enforce via formatter. PEP 8 is deliberately silent. |
| Line length | Configure in formatter (88 for black/ruff, 79 for strict PEP 8). Don't manually wrap. |
| Imports | isort-ordered: stdlib → third-party → local. One import per line for from imports. |
Naming
Conventions
| Scope | Style | Example |
|---|---|---|
| Modules, packages | snake_case |
crypto_key.py, utils/ |
| Functions, methods | snake_case (verbs) |
get_url(), calculate_checksum() |
| Variables | snake_case (nouns) |
raw_payload, user_registry |
| Classes | PascalCase |
HttpClient, TokenParser |
| Constants | SCREAMING_SNAKE |
MAX_RETRIES, DEFAULT_TIMEOUT |
| Private | _leading_underscore |
_internal_cache, _validate() |
| Name-mangled | __double_leading |
__secret (rarely needed) |
| Dunder | __name__ |
Reserved for the language. Never invent new ones. |
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 · 517 lines · 110 tokens per session scan A 2688b6ae2784
python is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 110 tokens to every session and 4,418 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…