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/specnpx skills add nrdxp/predicate --skill specgit 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 | $0.00063 | $0.03795 |
| Opus 5 | $0.00032 | $0.01898 |
| Sonnet 5 | $0.00013 | $0.00759 |
| Haiku 4.5 | $0.00006 | $0.00380 |
Grade A, and why
spec 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SPEC — Normative Specification Workflow
Identify → Formalize → Verify → Record → Connect
Verification Dual — symbolic path. SPEC produces the normative constraint artifacts that are checked by the symbolic half of the Verification Dual: every constraint this workflow formalizes becomes a deterministic evaluator target (a test invariant, a type-level proof obligation, or a model-checker input) that closes a condition on the symbolic path. Routed at the moment of specifying invariants and behavioral contracts (rules.md §5).
This workflow defines the C.O.R.E. Specification phase. The objective is to define high-density normative constraint vectors (behavioral contracts) that prune the phase-space of valid trajectories during code generation. Where /form describes the system's states and transitions (coalgebraic dynamics), /spec declares what MUST hold (modal specification) and translates these constraints into test invariants.
Philosophy
A model is a representation. A specification is a contract.
Models are descriptive — they map the state-space and operational dynamics. Specifications are normative — they declare invariants that must remain stable and transition conditions that are permitted. This distinction maps precisely to the behavior/specification duality formalized in SDMA §11 (Stone duality: coalgebraic dynamics ↔ modal specification).
Without explicit specifications, sequence walks rely on stochastic priors. Every corrective feedback loop caused by trajectory drift is the cost of a missing specification. SPEC minimizes this drift by establishing explicit, deterministic constraints before execution, translating them into executable test suites.
Scope
[!IMPORTANT] SPEC produces normative constraint artifacts — declarations of what a system MUST, SHOULD, MUST NOT, and MAY do. It is NOT structural modeling (that's
/form) and NOT implementation (that's/core); strategic planning and exploration are the standing Planning Invariants and Sketch Principle, not workflows you switch into. If you find yourself describing ontology without constraints, you're in/formterritory. If you find yourself evaluating approaches rather than declaring constraints, you've left SPEC for strategy.
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 · 309 lines · 63 tokens per session scan A 4c58d0a46cb5
spec is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 63 tokens to every session and 3,795 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…