Findings & checks · 2 flagged
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · plugins/runapi-mcp/commands/balance.md
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
- Delete blanket "don't ask / no need to confirm" directives from the skill.
- If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Trace & refs
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · plugins/runapi-mcp/commands/setup.md
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
- Delete blanket "don't ask / no need to confirm" directives from the skill.
- If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Trace & refs
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Agentic Plugin Marketplace
Production-ready agentic workflow building blocks: 88 plugins, 194 agents, 158 skills, 106 commands — built for Claude Code and consumed natively by OpenAI Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot from a single Markdown source.
[!NOTE] One source-of-truth (plugins/), five harnesses. Each harness gets idiomatic, harness-native artifacts — not lowest-common-denominator translations. See docs/harnesses.md for the capability matrix.Quick start
Pick your harness:
Claude Code
/plugin marketplace add wshobson/agents
/plugin install python-development # or any of 88 plugins→ Full Claude Code setup, troubleshooting, and plugin catalog
Codex CLI · Cursor · OpenCode · Gemini CLI · Copilot
Codex and Cursor install natively from the committed registries (which point at the source plugins/):
npx codex-marketplace add wshobson/agents # Codex; then install individual plugins
# Cursor: add the marketplace, then `/plugin install <name>` (reads .cursor-plugin/ + source)Gemini and OpenCode install via clone + generate (the transformed trees are gitignored):
gh repo clone wshobson/agents ~/agents && cd ~/agents
make generate HARNESS=gemini && gemini extensions install . # Gemini
make install-opencode # OpenCode (runs generate + symlinks)Setup details and per-harness gotchas: docs/harnesses.md. Gemini-specific setup: GEMINI.md (also auto-loaded by Gemini CLI).
What's inside
| Count | What it is | |
|---|---|---|
| Plugins | 88 | Granular, single-purpose installable units (85 local + 3 external via git-subdir) |
| Agents | 194 | Domain experts (architecture, languages, infra, security, data, ML, docs, business, SEO) |
| Skills | 158 | Modular knowledge packages with progressive disclosure (load when activated) |
| Commands | 106 | Slash commands: scaffolding, security scans, test gen, infrastructure setup |
| Orchestrators | 16 | Multi-agent coordination workflows (full-stack, security, ML, incident response) |
Browse the catalog: docs/plugins.md · docs/agents.md · docs/agent-skills.md
How it works
Each plugin is isolated and composable: agents, commands, and skills are auto-discovered from directory structure. Installing a plugin loads only its components into context — not the whole marketplace.
plugins/python-development/
├── .claude-plugin/plugin.json
├── agents/ # 3 Python agents (python-pro, django-pro, fastapi-pro)
├── commands/ # 1 scaffolding command
└── skills/ # 16 specialized skills (async, testing, packaging, …)Tiered model strategy:
| Tier | Model | Use |
|---|---|---|
| 0 | Fable 5 | Longest-horizon autonomous work — large migrations, multi-hour runs (opt-in, premium cost) |
| 1 | Opus | Architecture, security, code review, production-critical |
| 2 | inherit | User-chosen — backend, frontend, AI/ML, specialized |
| 3 | Sonnet | Docs, testing, debugging, API references |
| 4 | Haiku | Fast operational tasks, SEO, deployment, content |
Multi-harness support
This marketplace ships to five agentic harnesses from one Markdown source. Each adapter emits harness-native artifacts (not lowest-common-denominator translations):
| Harness | Generates | Notes |
|---|---|---|
| Claude Code | (source-of-truth) | Native marketplace.json + plugins/ |
| Codex CLI | .agents/plugins/marketplace.json + plugins/*/.codex-plugin/plugin.json (committed); .codex/skills/, .codex/agents/ (gitignored) | 8 KB skill cap respected; commands → skills |
| Cursor | .cursor-plugin/, .cursor/rules/ | Thin marketplace + curated rules; reuses .claude/ |
| OpenCode | .opencode/agents/, .opencode/commands/, .opencode/skills/ | permission: block from tools: allowlist; OpenCode-safe skill names |
| Gemini CLI | skills/, agents/, commands/ (TOML) | Native skills + subagents (April 2026 spec) |
| Copilot | .copilot/agents/, .copilot/skills/, .copilot/commands/ | Markdown agent profiles + SKILL.md skills + commands-as-skills; model maps to native Claude models |
make generate-all # all five
make validate # structural checks
make garden # drift / dead-link / cap detectionCodex and Cursor install from source via committed registries; Gemini and OpenCode install via clone + make.
→ Full capability matrix and per-harness deep-dives
Quality evaluation
plugin-eval is a three-layer evaluation framework for measuring and certifying plugin/skill quality:
- Static — deterministic structural analysis (<2s, free)
- LLM Judge — semantic evaluation across 4 dimensions (~30s, Haiku + Sonnet)
- Monte Carlo — statistical reliability via 50-100 simulated runs (~2-5 min)
uv run plugin-eval score path/to/skill --depth quick
uv run plugin-eval certify path/to/skill→ PluginEval framework documentation
Documentation map
Detail lives in docs/. Read in this order:
- [docs/plugins.md](docs/plugins.md) — full catalog of all 88 plugins
- [docs/agents.md](docs/agents.md) — all 194 agents by category
- [docs/agent-skills.md](docs/agent-skills.md) — 158 skills with progressive disclosure
- [docs/usage.md](docs/usage.md) — commands, workflows, examples
- [docs/architecture.md](docs/architecture.md) — design principles
- [docs/harnesses.md](docs/harnesses.md) — cross-harness capability matrix
- [docs/authoring.md](docs/authoring.md) — portable-content style guide
- [docs/plugin-eval.md](docs/plugin-eval.md) — quality evaluation framework
- [docs/round-trip-results.md](docs/round-trip-results.md) — real-CLI verification recipes
Gemini-specific setup: GEMINI.md. All other harness setup, capability deltas, and gotchas live in docs/harnesses.md.
Contributing: CONTRIBUTING.md · Authoring: docs/authoring.md
External Memory Integration
Pensyve is included as an external git-subdir entry for Claude Code. Pensyve also maintains direct upstream integrations for this marketplace's other supported harnesses.
| Harness | Pensyve integration |
|---|---|
| Claude Code | /plugin install pensyve from this marketplace (integrations/claude-code) |
| Codex CLI | integrations/codex-plugin |
| Cursor | integrations/cursor |
| OpenCode | integrations/opencode-plugin |
| Gemini CLI | gemini extensions install https://github.com/major7apps/pensyve |
| Copilot | .copilot/ in repo root or ~/.copilot/ via make install-copilot |
License
MIT — see LICENSE.