instructions, skills and agents to improve your AI coding assistant
Skill Claude CodeCodex
Scaffold or match Angular admin CRUD entity slices (model/conf/service, thin feature component, protected routes, resolvers). Use when adding an administrable entity to an Angular admin app.
Skill Claude CodeCodex
Create predictable, actionable code-audit reports in a strict Markdown contract and validate them before publication. Use when an audit agent reports bugs, security findings, performance risks, or code-quality issues for CI workflows, GitHub issues, or other automated consumers.
Skill Claude CodeCodex
Scaffold or match Docker/Compose templates (non-root users, BuildKit secrets, Traefik labels, compose anchors). Use when adding Dockerfiles, compose services, or docker lifecycle scripts.
Skill Claude CodeCodex
Scaffold or match Node.js Express resource templates (routes, entities, services, middlewares, jobs). Use when adding a new Express resource, wiring cache sub-stacks, or copying an existing service pattern.
Skill Claude CodeCodex
Scaffold or match PostgreSQL + Liquibase schema templates (views, INSTEAD OF triggers, history, soft-delete, seeds). Use when adding entities, triggers, or changelog SQL under db/liquibase.
Skill Claude CodeCodex
Scaffold or match a VitePress product docs site (package.json, config.mjs, home/guide pages, mermaid, dev dockerfile, Pages workflow). Use when adding or updating documentation under a user-supplied docs root.
Skill Claude CodeCodex
Reference and adapt reusable k6 performance-test patterns. Use when scaffolding API load scenarios, Dockerized k6 execution, HTML and JSON reports, or CI benchmark tracking.
Skill Claude CodeCodex
Reference and adapt reusable RESTler API fuzzing patterns. Use when scaffolding spec-driven grammar compilation, Dockerized RESTler execution, token-refresh authentication, or CI fuzzing gates.
Skill Claude CodeCodex
Extract technical specifications from existing code as Markdown files under a specs directory and validate them before treating the task as done. Use when a spec-from-code agent, documentation agent, or CI step must emit structured docs/specs (or equivalent) with purpose, inputs, outputs, side effects, and tests.
Skill Claude CodeCodex
Structure, author, and validate persistent Think and Plan records (think.md and plan.md) from backlog issues before agents write code, following the Agentic Software Factory. Use when a Think Planner agent or planning session explores options, binds Forge assets, sets the blast radius, and sequences atomic…
Skill Claude CodeCodex
Declaratively assert that structured Markdown or text artifacts strictly adhere to schema contracts, required markers, heading hierarchies, and line constraints without custom scripts.
Skill Claude CodeCodex
Mechanically prevent agents from introducing unvetted, unprompted, or banned dependencies into package.json manifests by comparing working tree changes against git HEAD.
Skill Claude CodeCodex
Mechanically verify that database migrations and stateful changes can be cleanly applied, rolled back, and re-applied without syntax errors or dirty state.
Skill Claude CodeCodex
Assert that code modifications stay strictly within authorized path bounds and diff churn limits, preventing accidental file contamination and unbounded refactorings. Use when an agent completes a surgical code edit, before committing code, or during CI PR gating.
Skill Claude CodeCodex
Mechanically prevent agents from introducing hardcoded credentials, cloud API keys, private key blocks, or platform tokens into git diffs or source code.
Skill Claude CodeCodex
Execute multi-stage verification pipelines (linting, type checking, test suites, schema validation) and emit structured diagnostics for agent self-repair before declaring completion.
Skill Claude CodeCodex
Mechanically verify that AI-generated tests are genuinely falsifiable by temporarily unpatching source code to prove that tests fail when the bug is present, rejecting vacuous and tautological tests.
Skill Claude CodeCodex
Drive the Code stage one plan step at a time with persistent progress, enforce the fix-loop limit, and guard agent branches. Use when a Code agent implements a validated plan.md, when it records a step result or failure, or before committing to check the branch is short-lived and correctly named.
Skill Claude CodeCodex
Check the health of Persistent Context and prepare the weekly Persistent Context & Controls review: lint instruction files (missing description, broad applyTo, the everything instruction, near-duplicates, dangling skill/agent/prompt references, secrets, stale files, count growth) and keep an append-only corrections…
Skill Claude CodeCodex
Classify the differences between two OpenAPI 3.x JSON documents (or two JSON Schemas, with local $ref resolved) as BREAKING or compatible, and fail on any breaking change unless an Accepted, human-signed decision record is supplied. Use when the agent loop or CI (Prove stage) must guarantee that public interfaces and…
Skill Claude CodeCodex
Fail a change that weakens a deterministic control (deleted or skipped tests, lowered thresholds, disabled workflow steps, edited control files, added suppressions, removed assertions, production credentials in agent workflows) and enforce the bug rule (the failing check is committed before the fix). Use in the Code…
Skill Claude CodeCodex
Prove that every acceptance criterion (AC- ) in a plan.md has at least one passing test and that no test mapped to a criterion failed, by reading JUnit XML or Jest/Vitest JSON reports and printing a criterion-by-criterion verdict table. Use when the agent loop or CI (Prove stage) must gate a change on Criteria Test…
Skill Claude CodeCodex
Structure, draft, validate, and track the Architect's decision records (docs/decisions/NNNN-slug.md) and escalations with a default date. Use when a Decision Scribe agent or session drafts a decision from a Think record, when CI validates numbering, supersession, signatures, or the think.md decision-record…
Skill Claude CodeCodex
Record and compute the Agentic Software Factory metrics from an append-only event log (metrics/events.jsonl): validate and append events, then print a Markdown or JSON report of flow, per-stage, AI-leverage, and outcome metrics with targets and ok/warn/unknown status. Use when a pipeline must emit a delivery event…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: