Neutral source of coding standards, agent roles, skills, and workflows, rendered to native config for Claude Code, Codex, and Amp. Successor to agent-workflows.
This repository also configures its own agents. See what coding-agent-workflows tells them →
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Design or critique evals and benchmarks for AI agents, dev tools, RAG, and repo-scale automation: task selection, contamination, metrics, statistical validity. Use to choose metrics or judge whether an improvement is real.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Capture architectural decisions made during coding sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Binary search for root cause: define a search space and a pass/fail oracle, then halve the space each step until the culprit commit, config key, or dependency is isolated. Works across git history, configuration, dependencies, or code modules.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Structured brainstorming with research-driven exclusion zones and shape-uniqueness enforcement. Forces divergent thinking through volume and a hard constraint: no idea may take the same shape as any prior art or any earlier idea. Use when exploring solutions to a problem, designing features, or when the obvious…
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts token usage 75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or…
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Review changes for security, correctness, and maintainability; require behavioral properties and evidence for risky state, concurrency, and core-logic changes.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter project instruction file. Use when joining a new project or setting up agent guidance in a repo.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Index of this project's coding-practice rules — architecture, coding style, testing, security, git workflow, task management, context layering, anti-slop, performance, and language-specific rules. The thin always-on essentials live in .claude/rules/common/house-rules.md; the full per-topic detail ships under…
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Structured debate and refinement. Independent advocates argue competing positions and trade-offs over divergent findings, then converge on a refined synthesis. Pairs with diverge.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Essence extraction via progressive compression. Chained compressors each halve the previous output while keeping what matters; what each layer drops reveals the priority hierarchy.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Multi-perspective divergent research. N independent agents with uncorrelated context explore a question from different angles, then synthesize into one analysis and PRD.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Thin methodology for end-to-end tests of critical user journeys — define journeys by risk, use semantic locators and condition-based waits, quarantine flaky tests with a tracked reason, and capture artifacts on failure. Use when adding or stabilizing E2E coverage; the e2e-runner agent applies it in depth.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Record a "don't do X here, it breaks Y" lesson into AGENTS.md so an agent doesn't repeat a mistake. Dedupes against CLAUDE.md/instincts before writing, promotes generalizing lessons out of memory, and keeps AGENTS.md under budget. Use after a bug, regression, or near-miss, or when the user says "capture this" / "make…
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Dependency-aware execution workflow for durable task stores. Selects ready work, runs independent tasks in isolated worktrees, verifies trusted branches, converges them onto one integration branch, and closes only landed work.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Stress-test an ambiguous or complex plan until its implementation decisions are shared and explicit. Use before coding when unresolved trade-offs materially affect the design.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Prospective failure narratives. Independent agents each write a story from a future where the project failed for a different root cause, synthesized into a risk registry with severity ratings and mitigations.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Map the tribal knowledge of a codebase into per-area COMPASS.md files — the why, the gotchas, and how each area connects — for existing repos and as they grow. Use when the user says "map this codebase", "generate compass files", "refresh the compass", or after a significant area changes.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases. Use when parsing quizzes, forms, invoices, or documents with repeating structure and cost matters.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Review a repository for long-term architectural leverage rather than code quality — system structure, module boundaries, dependency graph, coupling, and drift. Produces a ranked set of highest-ROI improvements with evidence, effort, and risk. Use when asked to review the architecture, assess a codebase's…
sjarmak/coding-agent-workflows
Skill Claude Code
Run the diverge → converge → premortem pipeline to produce a risk-annotated PRD.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Review a non-trivial code change for correctness, security, maintainability, and unnecessary complexity. Use after implementation and before a PR or release; use simplify or slop-check for narrower cleanup questions.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Build-order planning via competing sequencing strategies. Independent agents each propose a different build order for a chosen design, synthesized into a recommended plan with milestones, dependencies, and risks.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
sjarmak/coding-agent-workflows
Skill Claude CodeCodex
Reduce a diff to its essential complexity, removing dead paths, over-engineering, premature abstraction, and incidental churn, without changing behavior.
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: