Instructions file
Instructions for dean0x/devflow, covering devflow development guide, purpose, architecture overview, project structure and development loop.
19 yesterday B 10,907 tokens
original MIT
Code
02Agent
Autonomous task implementation on feature branch. Implements, tests, and commits.
19 yesterday A 17 tokens
original MIT
Design
03Agent
Design analysis agent with preloaded mode skills. Modes: gap-analysis (completeness, architecture, security, performance, compliance, consistency, dependencies), design-review (anti-pattern detection).
19 yesterday A 39 tokens
original MIT
Diagnose
04Agent
Proactive bug finding agent with static+semantic analysis. Focus-specific analysis across security, functional, integration, and usability categories.
19 yesterday A 28 tokens
original MIT
Evaluate
05Agent
Validates implementation aligns with original request and plan. Catches missed requirements, scope creep, and intent drift. Reports misalignments for Code agent to fix.
19 yesterday A 34 tokens
original MIT
Git
06Agent
Unified agent for all git/GitHub operations - issues, PR comments, tech debt, releases.
19 yesterday A 21 tokens
original MIT
Knowledge
07Agent
Structures codebase exploration into a feature knowledge base and registers it in the index cache.
19 yesterday A 18 tokens
original MIT
Learning
08Agent
Background decisions maintenance agent — claims the pending learning queue, detects architectural decisions and pitfalls from captured turns, and curates the decisions ledger. Spawned as a background agent by the session-start directive when the queue is non-empty.
19 yesterday A 47 tokens
original MIT
Research
09Agent
Multi-type research agent with dynamic skill loading. Receives research type, loads domain-specific skill, produces structured findings.
19 yesterday B 25 tokens
original MIT
Review
10Agent
Universal code review agent with parameterized focus. Dynamically loads pattern skill for assigned focus area.
19 yesterday A 21 tokens
original MIT
Scrutinize
11Agent
Self-review agent that evaluates and fixes implementation issues using 9-pillar framework. Runs in fresh context after Code agent completes.
19 yesterday A 29 tokens
original MIT
Simplify
12Agent
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
19 yesterday A 32 tokens
original MIT
Skim
13Agent
Codebase orientation using rskim to identify relevant files, functions, and patterns for a feature or task.
19 yesterday A 23 tokens
original MIT
Synthesize
14Agent
Combines outputs from multiple agents into actionable summaries (modes: exploration, planning, review, bug-analysis, design, research).
19 yesterday A 29 tokens
original MIT
Test
15Agent
Scenario-based QA agent. Designs and executes acceptance tests from criteria and implementation. Reports pass/fail with evidence — never fixes code.
19 yesterday A 28 tokens
original MIT
Triage
16Agent
Validates review issues against blast-radius disposition matrix. Assigns one verdict per issue. Never edits code.
19 yesterday A 24 tokens
original MIT
Validate
17Agent
Dedicated agent for running validation commands (build, typecheck, lint, test). Reports pass/fail with structured failure details - never fixes.
19 yesterday A 30 tokens
original MIT
release
18Command
Release project using adaptive learned configuration.
19 yesterday A 6 tokens
original MIT
Skill Claude CodeCodex
This skill should be used when the user asks to "add accessibility", "check ARIA", "handle keyboard navigation", "add focus management", or creates UI components, forms, or interactive elements. Provides WCAG 2.2 AA patterns for keyboard navigation, ARIA roles and states, focus management, color contrast, and screen…
19 yesterday A 73 tokens
original MIT
Skill Claude CodeCodex
Canonical algorithm for consuming DECISIONSCONTEXT index — scan index, identify relevant entries, Read full bodies on demand, cite verbatim IDs inline.
19 yesterday A 33 tokens
original MIT
Skill Claude CodeCodex
Consumption algorithm for FEATUREKNOWLEDGE variable — pre-computed feature context.
19 yesterday A 20 tokens
original MIT
architecture
22Skill Claude CodeCodex
This skill should be used when reviewing code for SOLID violations, tight coupling, or layering issues.
19 yesterday A 22 tokens
original MIT
Skill Claude CodeCodex
This skill should be used when the user asks to "validate input", "parse request data", "handle form data", "add Zod schema", "sanitize user input", or creates API endpoints and system boundaries. Provides parse-don't-validate patterns with schema validation for type-safe boundary enforcement and hostile input defense.
19 yesterday A 67 tokens
original MIT
complexity
24Skill Claude CodeCodex
This skill should be used when reviewing code for high cyclomatic complexity, deep nesting, or long functions.
19 yesterday A 24 tokens
original MIT