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/formnpx skills add nrdxp/predicate --skill formgit 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 | $0.00070 | $0.02605 |
| Opus 5 | $0.00035 | $0.01303 |
| Sonnet 5 | $0.00014 | $0.00521 |
| Haiku 4.5 | $0.00007 | $0.00261 |
Grade A, and why
form 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FORM Protocol v2.0 (Control-Theoretic Modeling)
Identify → Select → Construct → Validate → Record → Connect
This workflow defines the C.O.R.E. Modeling phase. The objective is to define the formal structural representation of a domain, establishing the state space, transition relationships, and coalgebraic dynamics. This serves as the structural foundation from which normative constraints and test invariants are derived.
Philosophy
Formal models are the bridge between empirical observations and proof. An olog, a coalgebra, a session type specification — each makes implicit relationships explicit and mathematically verifiable. Without formal models, sequence trajectories are guided by anthropomorphic verbal descriptions that cannot be checked or formally composed.
FORM provides the procedure for constructing these structural representations. The sdma skill defines a foundational toolkit of categorical, coalgebraic, and information-theoretic isomorphisms. The principle of minimal representation governs selection: choose the simplest mathematical formalism that faithfully captures the domain's structure, and use it to map the state space for subsequent verification loops.
Scope
[!IMPORTANT] FORM produces formal model documents — either creating new ones from
templates/MODEL.mdor scrutinizing existing documents (protocol specs, whitepapers, design docs) through the SDMA lens. It is structural analysis, not planning, exploration, or implementation: strategic planning and exploration are the standing Planning Invariants and Sketch Principle, and implementation is/core. If you find yourself writing code or redesigning architecture, you've left FORM territory.
Dual-Mode Operation
MODEL operates in two modes, determined by context:
Create Mode
Trigger: No existing document specified. The human requests a formal model for a domain or problem.
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 · 261 lines · 70 tokens per session scan A 93138d2848f2
form is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 70 tokens to every session and 2,605 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 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…