nrdxp

38 mods across 1 repository, 10 stars between them.

predicate

01

nrdxp/predicate

Plugin Claude Code

Predicate catalogs itself: the rulesets, skills, and workflows live in this checkout.

10 8d ago A tokens not measured original MIT

predicate

02

nrdxp/predicate

Plugin Claude Code

Reusable agent rulesets (rules), skills, and workflows for agentic coding assistants.

10 8d ago A tokens not measured original MIT

predicate AGENTS.md

03

nrdxp/predicate

Instructions file CodexOpenCode

Instructions for nrdxp/predicate, covering agents.md — predicate, goal, formal substrate, requirements (for predicate to be useful) and invariants (soundness).

10 8d ago A 1,551 tokens original MIT

survivor

04

nrdxp/predicate

Skill Claude CodeCodex

When planning, run the /ghost workflow to frame the work, then proceed.

10 8d ago A 0 tokens original MIT

ai-audit

05

nrdxp/predicate

Skill Claude CodeCodex

SOP for auditing AI-generated code. Trigger when: Reviewing, refactoring, or cleaning up AI-generated code to prevent regressions or hallucinated APIs. Prompt contains: /ai-audit, code audit, AI cleanup, common flaws.

10 8d ago A 54 tokens original MIT

api-audit

06

nrdxp/predicate

Skill Claude CodeCodex

Protocol for auditing API surface coherence and type safety. Trigger when: Evaluating API designs, interface type safety, or design elegance. Prompt contains: /api-audit, API surface, API coherence, type safety.

10 8d ago A 49 tokens original MIT

boundary

07

nrdxp/predicate

Skill Claude CodeCodex

Normative sufficiency conditions for Initial Boundary Conditions (IBCs) and the SOP for the cheap-tier boundary refinement loop (/boundary). Trigger when: Crafting, auditing, or refining a prompt/IBC destined for an expensive (architect-class) model or an autonomous worker dispatch. Evaluating whether a task frame is…

10 8d ago A 104 tokens original MIT

campaign

08

nrdxp/predicate

Skill Claude CodeCodex

SOP for the architect-tier campaign workflow (/campaign): exhaustive survey, mitigation planning, tiered orchestration, and reconciliation. Trigger when: Running a multi-workstream initiative where an expensive architect-tier council surveys, plans, emits worker prompts, and judges landed work. Conducting…

10 8d ago A 110 tokens original MIT

chronicle

09

nrdxp/predicate

Skill Claude CodeCodex

Maintain and update the persistent project chronicle (docs/chronicle.md). Trigger when: The human requests a history summary or chronicle update. Starting work on a new codebase and needing context on its evolution. Prompt contains keywords: /chronicle, chronicle, project history, git log summary, history summary.

10 8d ago A 70 tokens original MIT

commit-hygiene

10

nrdxp/predicate

Skill Claude CodeCodex

Rules, conventions, and constraints for formatting git commit messages and committing at logical boundaries. Trigger when: Drafting, revising, or validating git commit messages. Pausing at commit boundaries under the CORE or CONTINUE workflows. Evaluating whether a changeset should be split into multiple commits.…

10 8d ago A 98 tokens original MIT

constitution

11

nrdxp/predicate

Skill Claude CodeCodex

Foundational ethics, authority hierarchy, and structural principles for the Predicate agent. Always-on law (composable system-prompt core): Truth>Harmony, Evidence>Authority, Halt>Assumption, Outcomes>Process — four ordered principles that govern every walk. Reference (by-moment): conflict resolution, ethics…

10 8d ago A 122 tokens original MIT

core

12

nrdxp/predicate

Skill Claude CodeCodex

SOP for the micro-execution C.O.R.E. phase. Trigger when: Implementing plan steps, managing code changes at commit boundaries, and verifying incremental progress. Navigating states: Absorb, Clarify, Plan, Execute. Prompt contains: /core, core workflow, absorb, clarify, execution invariants, commit boundary, verify…

10 8d ago A 76 tokens original MIT

council

13

nrdxp/predicate

Skill Claude CodeCodex

The LAW a council SEAT is bound by — deliberation protocol, pact obligations, governance, and decision-ledger recording — the discipline half of a seat. Trigger when: Holding a seat on a bound council (architect, lead-maintainer, process-auditor, or a summoned guest). Depositing an independent assessment, routing a…

10 8d ago A 135 tokens original MIT

doc-audit

14

nrdxp/predicate

Skill Claude CodeCodex

Trigger when auditing documentation, checking markdown link integrity, formatting tables, checking headers, or verifying absolute/relative paths.

10 8d ago A 27 tokens original MIT

doc

15

nrdxp/predicate

Skill Claude CodeCodex

SOP for structured documentation lifecycle. Trigger when: Designing, writing, reviewing, or auditing large-scale documentation structures. Navigating phases: Audit, Plan, Draft, Review, Verify. Prompt contains: /doc, doc workflow, audit, draft, review, verify, documentation debt.

10 8d ago A 62 tokens original MIT

documentation

16

nrdxp/predicate

Skill Claude CodeCodex

Writing quality guidelines, formatting conventions, and styling constraints for documentation. Trigger when: Writing, editing, or auditing documentation files, READMEs, markdown files, or guides. Modifying files with suffixes like: .md, .qmd, .txt, .rst. Prompt contains keywords: doc, documentation, spelling, grammar…

10 8d ago A 89 tokens original MIT

engineering

17

nrdxp/predicate

Skill Claude CodeCodex

Core technical, safety, and maintainability rules for codebase edits. Trigger when: Writing code, refactoring, modifying files, or creating unit tests. Proposing commits, reviewing git history, or auditing code quality. Modifying files in any programming language (e.g. .go, .rs, .py, .ts, .js, .c, .cpp). Prompt…

10 8d ago A 113 tokens original MIT

forge

18

nrdxp/predicate

Skill Claude CodeCodex

Conditional discipline for projects hosted on a git forge (GitHub, GitLab, Forgejo, …): branch↔PR mapping, self-contained PR prose, review-on-forge, merge consent, and the forge audit. Trigger when: Opening, updating, reviewing, or merging a pull/merge request. A campaign's integration branch is ready to surface on a…

10 8d ago A 119 tokens original MIT

form

19

nrdxp/predicate

Skill Claude CodeCodex

SOP for formal mathematical domain modeling. Trigger when: Creating new formal models or applying mathematical lenses to analyze existing specifications. Navigating phases: Identify, Select, Construct, Validate, Record, Connect. Prompt contains: /form, form workflow, categorical, coalgebraic, linear logic…

10 8d ago A 70 tokens original MIT

formal-foundations

20

nrdxp/predicate

Skill Claude CodeCodex

Mathematical foundations, logical structures, and formal verification guidance. Trigger when: Designing protocol contracts, formal specifications, verifying state spaces, or using proof assistants. Tasks involve: TLA+, Alloy, Lean, Coq, model checkers, invariants, temporal logic. Prompt contains keywords: formal…

10 8d ago A 91 tokens original MIT

git-review

21

nrdxp/predicate

Skill Claude CodeCodex

Goal-directed review of git history for change coherence. Trigger when: Analyzing project history, reviewing diffs, or checking commit messages for alignment. Prompt contains: /git-review, git history, commit log, change coherence.

10 8d ago A 51 tokens original MIT

go

22

nrdxp/predicate

Skill Claude CodeCodex

Idiomatic programming style, patterns, and conventions for Go (Golang) development. Trigger when: Writing, refactoring, reviewing, or debugging Go code. Files matching the pattern /.go (including go.mod, go.sum) are in the workspace or referenced. Tasks involve: go fmt, go test, go build, go vet, golangci-lint. Prompt…

10 8d ago A 112 tokens original MIT

hickey

23

nrdxp/predicate

Skill Claude CodeCodex

Structural simplicity review based on Rich Hickey's "Simple Made Easy" framework. Trigger when: Reviewing code for complected concerns, analyzing coupling, or simplifying code architecture. Prompt contains: /hickey, simple made easy, complect, decouple, compose.

10 8d ago A 59 tokens original MIT

humanizer

24

nrdxp/predicate

Skill Claude CodeCodex

Removing signs of AI-generated patterns from text. Trigger when: Refining documentation, comments, or summaries to sound natural and clear. Prompt contains: /humanizer, humanize, text cleanup, edit style.

10 8d ago A 47 tokens copy · 77% MIT