Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more
FAQ
agent-powerups is a Claude Code plugin with 200 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes prompt-evaluation-runner, red-team-eval-authoring, skill-evaluation-workbench. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
> /plugin marketplace add yeaight7/agent-powerups
Repo: yeaight7/agent-powerups
Agent Powerups is an Oh My Zsh-style collection of reusable skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for coding agents.
Today, this repo ships:
apx) with runnable local checksapx plugins inspection (apx plugins list)apx profiles for curated skill/plugin setsNative install is direct for humans. Safety boundaries stay around external tools, secrets, shell profiles, and MCP enablement.
| Path | Status | Notes |
|---|---|---|
skills/ | shipped | Reusable agent workflows such as systematic-debugging and writing-plans |
mcp/ | shipped | Local-first GitHub MCP config with check, smoke, and explicit install commands |
agents-md/ | shipped | Starter AGENTS.md templates |
commands/ | shipped | Review-first command prompts plus safe runnable checks |
hooks/ | shipped | Review-before-use hook recipes plus safe runnable checks |
workflows/ | shipped | Scenario guides |
plugins/ | shipped | Plugins with local-first discovery, validation, native install, and marketplace metadata (apx plugins list) |
scripts/ | shipped | Validation and tool-check helpers for this repo |
examples/ | shipped | Minimal safe setup examples |
If you are an agent working in a repo with Agent Powerups available, route tasks to capabilities yourself instead of waiting to be told:
Match first. On Claude Code the host already lists skills natively โ match the task to the narrowest fitting skill (plus obvious fits like no-fluff). On Codex, Gemini, or generic agents, start with apx discover.
Discover the rest โ anything not natively loaded (MCP configs, hooks, AGENTS.md templates, installed-only assets):
apx discover "<the user's task>" --target <codex|claude-code|gemini|generic> --json
apx info <chosen-asset> # what it is, when to use it, source path, next action
Read, apply, verify. Read the asset's SKILL.md (or file) before applying it; run apx check <asset> only if it declares external requirements; then verify the result against the task.
Gate risky assets. MCP configs and hooks are review-before-use โ surface them for approval, never auto-enable.
npm install -g agent-powerups
apx install claude --full
This installs the apx CLI globally and runs a full Claude Code setup โ copies skills, plugins, and commands into ~/.claude/ and patches your CLAUDE.md. Use --dry-run to preview changes first.
git clone https://github.com/yeaight7/agent-powerups.git
cd agent-powerups
npm install
npm run build
npm link
apx doctor
apx doctor --full
apx discover "fix a failing test regression" --target codex
apx inventory --target codex --json
apx list
apx list --json --verbose
apx info markitdown-file-intake
apx commands run ship-check
apx hooks run no-secrets-preflight --all
apx mcp check github-local --target generic
apx mcp smoke github-local --json
apx mcp install github-local --target codex --dry-run
apx install codex --dry-run
apx install codex
apx install claude
apx install gemini
apx install codex --full
apx install codex --verbose
Default native install copies all root skills and plugins into the selected agent root and writes a discovery-index.json beside them. Human output shows counts by default; use --verbose for per-file paths. If installed Agent Powerups guidance or discovery indexes are stale, apx install <agent> refreshes them by default. --full also stages support assets and another discovery index under agent-powerups/, then updates existing global instructions with a backup.
apx plugins list
apx plugins info dev-vitals
apx plugins validate --all
apx plugins install dev-vitals --target codex --dry-run
apx ask-codex "Return OK only" --json
apx ask-claude "Return OK only" --json
apx ask-gemini "Return OK only" --json
apx relay init second-opinion
apx relay start second-opinion --provider gemini
apx relay ask second-opinion "Review this plan" --json
apx relay status second-opinion
apx relay stop second-opinion
apx profiles list
apx profiles info safe-core
apx profiles plan safe-core --target codex
apx check markitdown-file-intake
apx check graphify
Use apx check only for assets that declare external requirements. A successful dependency check does not mean the skill or workflow was used correctly.
Preview supported dependency installers before asking for approval:
apx check defuddle --install-missing --dry-run
apx check markitdown-file-intake --install-missing --dry-run
apx check graphify --install-missing --dry-run
apx install markitdown-file-intake --target codex --dry-run
apx install ask-claude --target codex --dry-run
apx setup codex --dry-run
apx setup codex --mode minimal --yes # bootstrap only
apx setup codex --mode recommended --yes # main agent setup (recommended)
apx setup codex --mode full --yes # broad staging
apx setup is legacy compatibility and remains supported through at least v0.8.0. Prefer apx install <agent> for manual native install.
apx install <codex|claude|claude-code|gemini> [--verbose]
apx install <codex|claude|claude-code|gemini> --full [--verbose]
Default manual install:
skills/ -> <agent-root>/skills/<agent-root>/plugins/<agent-root>/extensions/Give your agent access to this repo and ask it to run:
apx list
apx profiles list
apx setup <codex|claude-code|gemini> --mode recommended --yes
Agent will inspect available skills/plugins, propose a plan, and apply it. This is the legacy compatibility path for agent-curated setup; manual setup should use apx install <agent>.
Agent setup docs:
python scripts/validate-skills.py
python scripts/validate-catalog.py
python scripts/validate-mirrors.py
python scripts/check-requirements.py
The shipped catalog changes often, so it is not enumerated here. Browse it from the CLI โ these surfaces are always current:
apx list # compact human browse of everything shipped
apx list --type skill # filter by category (skill, command, plugin, hook, mcp-config, ...)
apx discover "<your task>" # task-based: what should I use for this?
apx plugins list # available plugins
apx mcp list # available MCP configs
Human-facing categories: skills, commands, plugins, MCP configs, hooks, and
AGENTS.md templates (scripts, examples, and workflows are internal). See the taxonomy and
field definitions in docs/catalog-schema.md. Catalog assets also carry
a browsing tier: core, common, specialized, or experimental.
Compatibility claims in this repo are intentionally narrow:
| Asset class | Shipped today | Compatibility claim |
|---|---|---|
Root skills/ | yes | Generic text-based skills; some also mention known agent surfaces |
mcp/ | yes | MCP configs for local and remote servers (GitHub, Supabase, Vercel, Cloudflare, Exa, Atlassian, Browserbase, E2B, and more); github-local has a full check/smoke/install flow |
agents-md/ | yes | Plain text templates |
commands/ | yes | Review-first markdown command prompts; Claude Code and Codex targets where provided |
hooks/ | yes | Documentation recipes only; not installed automatically |
workflows/ | yes | Plain text scenario guides |
plugins/ | yes | Plugins with native install, marketplace metadata, and apx plugins inspection |
scripts/ | yes | Generic Python scripts |
examples/ | yes | Plain text setup examples only |
More detail: docs/compatibility.md
Most shipped skills are pure text and need no extra installation.
Current optional external tools used by shipped skills:
| Skill | Tool | Required | Install |
|---|---|---|---|
ask-codex | Codex CLI (codex) | yes for local advisor workflow | install/configure Codex CLI |
ask-claude | Claude Code CLI (claude) | yes for local advisor workflow | install/configure Claude Code CLI |
ask-gemini | Gemini CLI (gemini) | yes for local advisor workflow | install/configure Gemini CLI |
markitdown-file-intake | Microsoft MarkItDown (markitdown) | yes for conversion workflow | python -m pip install markitdown |
defuddle | Defuddle CLI (defuddle) | yes for Defuddle workflow | npm install -g defuddle |
graphify | Upstream Graphify CLI + Python package (graphify, graphifyy) | yes for graph workflow | uv tool install graphifyy or pipx install graphifyy or python -m pip install graphifyy |
pr-triage | GitHub CLI (gh) | optional | platform package manager |
Tool policy:
More detail: docs/tool-requirements.md and docs/installation.md
npm install
npm run build
npm link
apx doctor
apx doctor --full --json
apx list
apx list --json --verbose
apx inventory --target codex --json
apx discover "fix a failing test" --target codex --json
apx info markitdown-file-intake
apx check markitdown-file-intake
apx check graphify
apx ask-codex "Explain this code" --json
apx ask-claude "Review this patch" --json
apx ask-gemini "Brainstorm test cases" --json
apx relay start second-opinion --provider gemini --json
apx relay ask second-opinion "Review this plan" --json
apx relay stop second-opinion --json
apx ship-check --json
apx no-secrets-preflight --all --json
apx using-powerups
apx install codex --dry-run
apx install codex
apx install claude
apx install gemini
apx install codex --full
apx install markitdown-file-intake --target codex --dry-run
apx setup codex --dry-run
apx setup claude-code --dry-run
apx setup gemini --dry-run
apx setup codex --mode recommended --yes
apx setup claude-code --mode recommended --yes
apx setup gemini --mode recommended --yes
apx install <agent> is now the primary manual install path and writes native skills/plugins by default. apx setup <agent> is legacy compatibility for agent-curated setup, remains dry-run by default unless --yes is passed, and remains supported through at least v0.8.0; removal or aliasing requires a separate batch.
Extra surfaces:
apx mcp list
apx mcp print github-local --target claude-code
apx mcp check github-local --target claude-code --json
apx mcp smoke github-local --json
apx mcp install github-local --target codex --dry-run
apx mcp install github-local --target claude-code --dry-run
apx mcp write github-local --target generic --dest .agent-powerups/github-local.json
apx agents-md list
apx agents-md print typescript-app
apx commands list
apx commands print ship-check --target generic
apx commands run ship-check --full
apx hooks list
apx hooks print no-secrets-preflight
apx hooks run no-secrets-preflight --path README.md
apx workflows list
apx workflows print feature-iteration
apx plugins list
apx plugins info dev-vitals
apx plugins validate --all
apx plugins install dev-vitals --target codex --dry-run
apx profiles list
apx profiles info safe-core
apx profiles plan safe-core --target codex
apx relay init second-opinion
apx relay start second-opinion --provider gemini --json
apx relay ask second-opinion "Review this plan" --json
apx relay status second-opinion --json
apx relay stop second-opinion --json
To explicitly copy a skill into a local Codex-visible folder, choose the destination yourself:
apx install ask-claude --target codex --dest .agent-powerups/installed/ask-claude
Plugins ship under plugins/. They are registered in both .claude-plugin/marketplace.json and .codex-plugin/marketplace.json. Gemini CLI uses local extensions; each plugin includes gemini-extension.json and GEMINI.md.
apx plugins list to discover pluginsapx plugins info <name> to inspect a single pluginapx plugins info <name> --json to inspect contained skill, command, agent, and template metadataapx plugins validate --all to verify plugin structureapx plugins install <name> --target <codex|claude-code|generic> --dry-run before any writediscovery-index.json so contained assets are queryable directlyapx install <codex|claude|gemini> for full manual native installReview assets before loading them into a trusted agent environment.
See SECURITY.md and docs/security-model.md.
Contribution guide: CONTRIBUTING.md
Acknowledgements: ACKNOWLEDGEMENTS.md
MCP configs: docs/mcp-configs.md
Roadmap: roadmap.md
.claude-plugin/
marketplace.json
.codex-plugin/
marketplace.json
.gitattributes
.github/
workflows/
ci.yml
publish-github-packages.yml
release.yml
.gitignore
ACKNOWLEDGEMENTS.md
agents-md/
dbt-project/
AGENTS.md
ml-project/
AGENTS.md
open-source-maintainer/
AGENTS.md
python-library/
AGENTS.md
typescript-app/
AGENTS.md
AGENTS.md
assets/
agent-powerups-header-dark.svg
agent-powerups-header-light.svg
agent-powerups-social-media-preview.svg
agent-powerups-social-preview-optimized.gif
agent-powerups-social-preview.gif
svg-to-gif.py
catalog.json
CHANGELOG.md
CLAUDE.md
commands/
bug-check.md
claude-code/
build-fix.md
changelog.md
debug.md
doctor.md
implement.md
mcp-check.md
mcp-smoke.md
plan.md
release.md
review.md
ship-check.md
triage.md
visual-review.md
codex/
build-fix.md
changelog.md
debug.md
doctor.md
implement.md
mcp-check.md
mcp-smoke.md
plan.md
release.md
review.md
ship-check.md
triage.md
visual-review.md
generic/
build-fix.md
changelog.md
debug.md
doctor.md
implement.md
mcp-check.md
mcp-smoke.md
plan.md
release.md
review.md
ship-check.md
triage.md
using-powerups.md
visual-review.md
model-route.md
quality-gate.md
security-audit.md
CONTRIBUTING.md
docs/
authoring-guide.md
catalog-schema.md
compatibility.md
installation.md
mcp-configs.md
philosophy.md
plugin-bundles-schema.json
profiles-schema.md
security-model.md
setup/
claude-code.md
codex.md
gemini.md
tool-requirements.md
examples/
claude-code/
README.md
codex/
README.md
minimal/
README.md
gemini-extension.json
GEMINI.md
hooks/
cloud/
cloud-cli-guard.md
git/
large-diff-warning.md
mcp/
mcp-config-change-approval.md
mcp-elicitation-guard.md
mcp-write-guard.md
productivity/
auto-commit-message.md
dev-server-tmux-guard.md
handoff-completeness-check.md
handoff-summary.md
session-compaction-helper.md
session-context-restore.md
session-lifecycle-state.md
session-log.md
quality/
build-analysis-post.md
console-log-check.md
design-quality-check.md
doc-file-warning.md
generated-file-warning.md
lint-check.md
migration-review-required.md
pre-commit-quality-check.md
quality-gate-after-edit.md
test-gate.md
todo-fixme-blocker.md
typescript-post-edit-check.md
validation-required.md
safety/
dependency-review.md
destructive-bash-guard.md
env-file-mutation-approval.md
no-secrets-preflight.md
LICENSE
mcp/
claude-code/
atlassian.json
browserbase.json
cloudflare-docs.json
context7.json
e2b-sandbox.json
exa-search.json
fetch.json
filesystem-repo-scoped.json
git-local.json
github-local.json
github-remote.json
memory.json
playwright.json
postgres-readonly.json
sequential-thinking.json
supabase.json
time.json
vercel.json
codex/
atlassian.toml
browserbase.toml
cloudflare-docs.toml
context7.toml
e2b-sandbox.toml
exa-search.toml
fetch.toml
filesystem-repo-scoped.toml
git-local.toml
github-local.toml
github-remote.toml
memory.toml
playwright.toml
postgres-readonly.toml
sequential-thinking.toml
supabase.toml
time.toml
vercel.toml
generic/
atlassian.json
browserbase.json
cloudflare-docs.json
context7.json
e2b-sandbox.json
exa-search.json
fetch.json
filesystem-repo-scoped.json
git-local.json
github-local.json
github-remote.json
memory.json
playwright.json
postgres-readonly.json
sequential-thinking.json
supabase.json
time.json
vercel.json
package-lock.json
package.json
plugin-bundles.json
plugins/
agent-evaluation-lab/
.claude-plugin/
plugin.json
.codex-plugin/
plugin.json
gemini-extension.json
GEMINI.md
skills/
prompt-evaluation-runner/
references/
eval-config-patterns.md
SKILL.md
red-team-eval-authoring/
references/
redteam-grader-checklist.md
SKILL.md
skill-evaluation-workbench/
references/
workbench-suite-model.md
SKILL.md
agentic-systems/
.claude-plugin/
plugin.json
.codex-plugin/
plugin.json
agents/
README.md
commands/
model-route.md
README.md
gemini-extension.json
GEMINI.md
skills/
agent-harness-design/
SKILL.md
canonical-advisor-routing/
SKILL.md
context-retrieval-loop/
SKILL.md
model-routing/
SKILL.md
tri-model-review/
SKILL.md
codebase-intelligence/
.claude-plugin/
plugin.json
.codex-plugin/
plugin.json
agents/
codebase-mapper.md
intel-updater.md
pattern-mapper.md
commands/
map-codebase.md
gemini-extension.json
GEMINI.md
skills/
context-retrieval-loop/
SKILL.md
local-rag-mcp/
references/
rag-tool-model.md
SKILL.md
managed-codebase-context/
references/
managed-session-checklist.md
SKILL.md
search-before-building/
SKILL.md
structured-code-search-mcp/
references/
code-search-tool-selection.md
SKILL.md
templates/
ARCHITECTURE.md
CONCERNS.md
CONVENTIONS.md
INTEGRATIONS.md
STACK.md
STRUCTURE.md
TESTING.md
codebase-maintenance/
.claude-plugin/
plugin.json
.codex-plugin/
plugin.json
agents/
codebase-cleaner.md
safe-refactorer.md
technical-debt-reviewer.md
commands/
cleanup.md
debt-audit.md
refactor-plan.md
safe-rename.md
gemini-extension.json
GEMINI.md
skills/
ai-slop-cleaner/
SKILL.md
architecture-simplification/
SKILL.md
context-retrieval-loop/
SKILL.md
dead-code-removal/
SKILL.md
dependency-cleanup/
SKILL.md
incremental-migration/
SKILL.md
naming-and-structure-cleanup/
SKILL.md
safe-refactor/
SKILL.md
test-preserving-refactor/
SKILL.md
connected-apps/
.claude-plugin/
plugin.json
.codex-plugin/
plugin.json
gemini-extension.json
GEMINI.md
skills/
deploy-pipeline-runbook/
SKILL.md
context-efficiency/
.claude-plugin/
plugin.json
.codex-plugin/
plugin.json
commands/
context-router.md
review-router.md
workflow-router.md
gemini-extension.json
GEMINI.md
data-engineering/
.claude-plugin/
plugin.json
.codex-plugin/
plugin.json
agents/
bigquery-cost-analyst.md
data-engineer.md
data-quality-reviewer.md
dbt-analytics-engineer.md
semantic-layer-reviewer.md
commands/
bigquery-cost-check.md
data-quality-check.md
dbt-model-review.md
semantic-change-check.md
gemini-extension.json
GEMINI.md
skills/
bigquery-cost-audit/
SKILL.md
data-quality/
SKILL.md
dbt-incremental-strategy-audit/
SKILL.md
dbt-preflight/
SKILL.md
dbt-strategy/
SKILL.md
metric-impact-analyzer/
SKILL.md
semantic-layer-change-review/
SKILL.md
sql-business-logic-review/
SKILL.md
debugging-diagnostics/
.claude-plugin/
plugin.json
.codex-plugin/
plugin.json
agents/
failure-diagnostician.md
flaky-test-investigator.md
reproduction-engineer.md
root-cause-debugger.md
commands/
create-repro.md
debug.md
diagnose-failure.md
trace-regression.md
gemini-extension.json
GEMINI.md
skills/
bug-hunt/
SKILL.md
failure-triage/
... 782 moreShowing a partial view of a very large repo.
ยฉ 2026 Flowy ยท Free and open source
Built for Claude Code ยท Not affiliated with Anthropic