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/sdmanpx skills add nrdxp/predicate --skill sdmagit 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 | $0.05523 |
| Opus 5 | $0.00044 | $0.02762 |
| Sonnet 5 | $0.00018 | $0.01105 |
| Haiku 4.5 | $0.00009 | $0.00552 |
Grade A, and why
sdma 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 — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structural Domain Modeling Atlas (SDMA)
Reference corpus — /form, /spec, boundary, engineering. This skill survives as the applied-methodology authority for formal domain modeling; the mandate to apply it is ambient, rooted in the workflows that invoke it as a lens. It is the form workflow's mathematical toolkit, the formalism-selection authority for spec's verification tier choices, and the structural vocabulary consulted by boundary and engineering. Where applicable, the formalisms in this atlas close conditions on the symbolic path of the Verification Dual (coalgebraic bisimulation, session-type checking, linear-type discipline) or supply the structural representation that the adversarial path reviews for coherence.
This skill provides the applied methodology for formal domain modeling. The mathematical foundations — SMC, Rosetta Stone, Curry-Howard, algebra/coalgebra duality — live in the formal-foundations skill (skills/formal-foundations/SKILL.md). This skill tells you how to wield them.
The SDMA covers what are arguably the most critical isomorphisms in computer science — the categorical, coalgebraic, linear, and information-theoretic bedrock. But it is a foundation, not a ceiling. The full landscape of mathematical formalism is available. The SDMA provides the root from which to reach for any relevant representation, guided by the principle of minimal representation: choose the simplest formalism that faithfully captures the domain's essential structure.
Part I — The Atlas
1. Functorial Data Migration in Practice
The formal definitions of schemas-as-categories and adjoint migration functors live in the formal-foundations skill. Here we focus on how to apply them.
Schema Design as Category Design
Treat every database schema as a small category S. This isn't metaphorical — it's a precise correspondence:
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 · 442 lines · 89 tokens per session scan A 72b4ca739d64
sdma 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 5,523 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…