1,927 tagged coding-agents, measured the same way as everything else here.
Browse within: codex-cli 115agent-orchestration 104context-engineering 79agentic-coding 76software-engineering 70agentic-workflow 67open-source 66pi 66agent-memory 65bootstrap 65agent-harness 64agent-workflows 57agent-workspaces 46ai-native 46
Skill Claude CodeCodex
Operate Forge's singular global Main Agent during Product Genesis and portfolio-level discovery. Use when turning a rough idea into a named, revisioned Project Charter; pressure-testing intent with at most two consequential questions per turn; doing bounded public research; presenting an exact user approval target…
Skill Claude CodeCodex
Implement, review, or evolve Forge's cross-role Project orchestration contracts across the singular Main Agent, one Project Agent per Project, Task Workers, reviewers, users, and system authority. Use for architecture, persistence, API, migration, policy, or acceptance work involving Product Genesis, Charter approval…
Skill Claude CodeCodex
Operate the singular Project Agent for exactly one Forge Project after Charter-backed handoff. Use when verifying Project startup, doing bounded research, drafting revisioned Project Documents and Decisions, proposing or reconciling an execution baseline, creating and managing traceable Tasks, coordinating independent…
majiayu000/awesome-goal-prompts
Skill Claude CodeCodex
Create, tighten, or review runnable /goal contracts for coding agents such as Codex, Claude Code, Cursor, and similar agent tools. Use when the user asks to write, make, generate, improve, productize, or critique a goal prompt, rescue contract, GOAL.md-style task, done-when contract, verification prompt, stop-rule…
Skill Claude CodeCodex
Use Flameox to investigate runtime performance, memory, execution, scaling, GPU kernels, inference, and reliability with preserved evidence and explicit claim quality.
Skill Claude CodeCodex
Part of deploybot
Inspect and operate the full DeployBot delivery pipeline. Use when the user invokes DeployBot, asks for thread, PR, queue, CI, deployment, blocker, repair, integration, or timing status, explicitly says deploy, or asks the coordinator to deliver authorized pull requests.
Skill Claude CodeCodex
Part of deploybot
Prepare, review, enqueue, and land GitHub pull requests through a provider-neutral agent merge queue. Use when a PR becomes ready, configured review feedback must be addressed, the user says deploy, or queued changes need safe conflict-aware ordering.
Skill Claude CodeCodex
Investigate stuck runs and execution failures by tracing Symphony and Codex logs with issue/session identifiers; use when runs stall, retry repeatedly, or fail unexpectedly.
Skill Claude CodeCodex
Land a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion.
Skill Claude CodeCodex
Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.
Skill Claude CodeCodex
Visual reasoning discipline for verifying UI and Three.js work with the SceneProof CLI. Use whenever a change can alter rendered output — components, styles, layout, SVG, canvas, scenes, cameras, lights, materials, animation — or whenever about to claim that something "looks right", "is visible", or "renders…
Skill Claude CodeCodex
Optimize HarnessGym tensor-layout kernelplan.json tasks with a generated MCP server for plan validation, dev/final benchmarking, trace analysis, rollback-safe search, candidate application, history comparison, and experiment ranking. Use when a task asks to minimize bestcycles for benchmark.py or tune tensor…
Skill Claude CodeCodex
Use for the H100 Triton fused RMSNorm + SiLU gate optimization task. Provides the workflow and MCP tooling for objective runs, rollback-safe config sweeps, source diagnostics, benchmark history, and final held-out verification.
BusyBee3333/sol-governed-codex
Skill Claude CodeCodex
Use when Codex work should route bounded implementation to lower-cost workers and reserve Sol for risky plan review or final evidence gates, or when installing or validating this workflow.
Skill Claude CodeCodex
Use when a task spans interface understanding, design-system memory, UI audits, design CI, Figma, shadcn or Tailwind code generation, research, or agent design workflows and needs the correct Memi capability selected.
Skill Claude CodeCodex
Part of memi
Use when reviewing or changing a React, Next.js, Tailwind, or shadcn interface and you need evidence-backed findings for accessibility, hierarchy, tokens, states, and responsive design before editing code.
Skill Claude CodeCodex
Part of memi
Use when a coding agent must design, scaffold, implement, or verify an iOS or macOS SwiftUI interface with Apple-platform state, accessibility, availability, testing, and Xcode evidence.
Skill Claude CodeCodex
Use for PACEflow internal full audit: run five independent review agents, verify evidence from code/tests/logs, de-duplicate findings, and produce a severity-ranked report for release gates or comprehensive code review.
Skill Claude CodeCodex
Part of paceflow
Use for PACEflow artifact fields and formats: task indexes, CHG/HOTFIX lifecycle operations, artifact-writer prompts, approvals, verification, and archive.
Skill Claude CodeCodex
Part of paceflow
Use for PACEflow-managed coding work: create, approve, resume, verify, close, or archive CHG/HOTFIX before project file edits.
Skill Claude CodeCodex
Keep remote slash-command skipping enabled by default, then reopen it only for bridge-safe commands while denying unsafe local commands with a friendly local response.
Skill Claude CodeCodex
Decide when to auto-refresh plugins after marketplaces change and when to defer to a manual /reload-plugins via the needsRefresh flag.
Skill Claude CodeCodex
Merge runtime-discovered commands into an existing command registry by deduping them against the enabled base surface and inserting them at a stable boundary before built-in commands.
Skill Claude CodeCodex
Part of deslop
Audit or apply subtractive cleanup for accumulated agent-created test bloat, verification theater, and defensive or fallback bloat while preserving independent external behavior. Invoke explicitly for semantic simplification, not generic refactoring.
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: