agents md commands

marcusquinn/aidevops

Command Codex

Subjective self-refinement with blind judging, Borda aggregation, and provider-agnostic model routing.

marcusquinn/aidevops

Command Codex

Deep research — produce a cited decision-grade research report and artifact bundle.

marcusquinn/aidevops

Command Codex

Goal-oriented mission entrypoint — set, view, or drive long-running objectives through the mission system.

coco-research/coco

Command

Auto-generated. Run python3 scripts/build-index.py to refresh.

KbWen/agentic-os

Command Claude Code

Execute the canonical workflow: .agent/workflows/app-init.md.

KbWen/agentic-os

Command Claude Code

Execute the canonical workflow: .agent/workflows/bootstrap.md.

KbWen/agentic-os

Command Claude Code

Execute the canonical workflow: .agent/workflows/spec-intake.md.

ajhcs/healthcare-agents

Command Claude Code

Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.

GeoloeG-IsT/agents-reverse-engineer

Command Claude Code

Start a new milestone cycle — update PROJECT.md and route to requirements.

GeoloeG-IsT/agents-reverse-engineer

Command Claude Code

Initialize a new project with deep context gathering and PROJECT.md.

GeoloeG-IsT/agents-reverse-engineer

Command Claude Code

Create detailed execution plan for a phase (PLAN.md) with verification loop.

wonsukchoi/domain-experts

Command Claude Code

Batch re-score shipped domain-expert roles against AUTHORING.md and flag/deprecate stale ones.

wonsukchoi/domain-experts

Command Claude Code

Scan a project and suggest domain-expert skills it would benefit from, then draft the ones the user picks.

wonsukchoi/domain-experts

Command

Route a task to the best-matching domain-experts role and reason as that expert.

bestcow/dear-agent

Command Claude Code

A command that updates the project’s HANDOFF.md file with the current session’s work and rebuilds the workspace index when needed. HANDOFF.md is the record of the project’s current state.

StringKe/std-agent

Command

A release command for publishing the next patch version of a Go project from its latest semantic version tag. It checks the build workflow, downloadable files, checksums, and installation result.

deepfusionlabs/deep-init

Command

Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.

deepfusionlabs/deep-init

Command

Tune a DeepInit run with buttons — depth, issue detection, outputs, scope, cost, and the freshness/notification settings (disable the nudge, change its cadence/time-window) — no flags to type. Opens a native multiple-choice picker, then runs.

deepfusionlabs/deep-init

Command

Upgrade DeepInit to the latest version — pulls the newest from the marketplace (on one confirm), then guides the host-correct reload. Ends the "is my plugin stale?" dance.

littlebearapps/contextdocs

Command

Generate, update, or audit AI IDE context files with AGENTS.md as the canonical shared context and tool-specific bridge files. Signal Gate principle — only what agents cannot discover: $ARGUMENTS.

littlebearapps/contextdocs

Command

Install, uninstall, or check status of Context Guard hooks for AI context file freshness: $ARGUMENTS.

littlebearapps/contextdocs

Command

Validate AI context file quality — signal-to-noise ratio, line budgets, stale paths, AGENTS-to-bridge consistency, and context health scoring: $ARGUMENTS.

TheSmuks/ai-project-template

Command

Review staged git changes for issues before committing.

ishands/upstack

Command Claude Code

Load and follow the skill at .agents/skills/core/check-progress/SKILL.md.