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/documentationnpx skills add nrdxp/predicate --skill documentationgit 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 | $0.00089 | $0.01690 |
| Opus 5 | $0.00044 | $0.00845 |
| Sonnet 5 | $0.00018 | $0.00338 |
| Haiku 4.5 | $0.00009 | $0.00169 |
Grade A, and why
documentation 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation
This skill governs how you write. Section 1 applies to all text you produce — code comments, chat responses, documentation. (Commit messages are governed by commit-hygiene, which owns that jurisdiction in the §5 routing table.) Section 2 applies when you are producing or editing a standalone document (README, guide, reference page, explanation, specification).
Section 1: Core Writing Principles
These rules are always active. They are non-negotiable.
1. Answer First
Lead with the conclusion, not the context. The reader's question should be answered in the first sentence or heading — background, caveats, and methodology come after. If someone stops reading after one paragraph, they should still have the answer.
2. Active Voice
Default to active voice. Use passive only when the actor is genuinely irrelevant or unknown. "The function returns an error" — not "An error is returned by the function."
3. Sentence Economy
One idea per sentence. Delete words that don't earn their place. If a sentence works without a word, remove that word. Prefer concrete language over abstract hedging.
4. Terminology Lock
Once you name a concept, use that name everywhere. Do not swap synonyms for variety — consistency beats prose elegance. If the codebase calls it a "store," never call it a "repository" or "database" in documentation. Terminological inconsistency is a documentation bug.
5. Scannable Structure
Readers scan before they read. Support this:
- Use meaningful headings (not "Overview" or "Introduction" — say what the section contains)
- Use bullet points for lists of 3+
- Bold key terms on first use
- Front-load important words in headings and list items
6. No Filler
Do not pad text with words that add no information.
[!CAUTION] Anti-Patterns (FORBIDDEN):
- ❌ Preamble walls: "In this section, we will discuss the various aspects of..."
- ❌ Restating the question: "You asked about X. X is an important topic. Let me explain X."
- ❌ Hedge-word padding: "It's worth noting that perhaps it might be considered..."
- ❌ Empty transitions: "Now let's move on to the next topic."
- ❌ Compliment-before-content: "Great question! That's a really interesting point."
- ❌ Metatext about your own process: "I'll analyze this step by step."
✅ Correct behavior: Start with the substance. If a paragraph's first sentence could be deleted without losing information, delete it.
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 · 136 lines · 89 tokens per session scan A 862716dd8679
documentation is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 89 tokens to every session and 1,690 once invoked, about $0.0004 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…