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/corenpx skills add nrdxp/predicate --skill coregit 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 | $0.00076 | $0.03086 |
| Opus 5 | $0.00038 | $0.01543 |
| Sonnet 5 | $0.00015 | $0.00617 |
| Haiku 4.5 | $0.00008 | $0.00309 |
Grade A, and why
core 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C.O.R.E. Protocol: Micro-Execution under the Verification Dual
Context → Obstacles → Resolution → Execution
This workflow defines the C.O.R.E. micro-execution phase. It guides a localized plan segment through a series of discrete state transitions (Context, Obstacles, Resolution, Execution), closing each step against the Verification Dual before committing: every step carries a deterministic evaluator (the symbolic path — test, compiler, linter) that must reach $\Delta E = 0$, and each commit boundary meets the Commit Gate (§3). C.O.R.E. is the task-scale instance of the Dual's symbolic path: drive a candidate edit to its evaluator's fixed point, then authorize the change through the ledger gate.
Scope
[!IMPORTANT] C.O.R.E. maps a localized plan segment (typically 2-3 commit boundaries) and manages the execution trajectory. It is execution, not strategy: high-level planning and the exploration of design alternatives are standing dispositions — the Planning Invariants and the Sketch Principle — not steps inside this workflow. If the sequence begins exploring design alternatives or modifying the architecture, it has exited C.O.R.E. space; the walk must immediately halt.
Grammar
# 1. TRAJECTORY METADATA
STATUS: [ABSORB | CLARIFY | PLAN | EXECUTE]
CONTROL_MODE: [MANUAL | AUTOMATIC] # MANUAL: halt at boundaries; AUTOMATIC: autocommit and continue if tests pass.
# 2. CONTEXT (The Initial Boundary Condition)
CTX:
GOAL: "User's objective (quoted verbatim)"
CONSTRAINTS:
- "Boundary condition 1"
FILES:
- path/to/target/file
# 3. OBSTACLES (Divergence Vectors)
# Populated in CLARIFY status; forces sequence freeze
OBSTACLES:
- "Uncertainty / contradiction 1"
# 4. TRAJECTORY PLAN (Discrete TDD Optimization Steps)
# Populated in PLAN/EXECUTE status
PLAN:
RATIONALE: "Mathematical / control rationale for this trajectory"
STEPS:
- ID: 1
INVARIANT: "Test assertion or property contract (TDD constraint)"
TEST_TARGET: "tests/test_file.py::test_name"
IMPL_TARGET: "src/file.py::function_name"
IMPL_DELTA: "Implementation edit to satisfy the invariant"
VALIDATOR: "pytest tests/test_file.py"
COMMIT: true # Marks a commit boundary
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 · 183 lines · 76 tokens per session scan A ff3ac74eabe0
core is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 76 tokens to every session and 3,086 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…