Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/monkey1wizard/golem-agents-legion/opencli-researchnpx skills add monkey1wizard/Golem-Agents-Legion --skill opencli-researchgit clone --depth 1 https://github.com/monkey1wizard/Golem-Agents-LegionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/monkey1wizard/golem-agents-legion/opencli-research)<a href="https://agentmods.dev/skills/monkey1wizard/golem-agents-legion/opencli-research"><img src="https://agentmods.dev/badge/skills/monkey1wizard/golem-agents-legion/opencli-research.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.00938 |
| Opus 5 | $0.00028 | $0.00469 |
| Sonnet 5 | $0.00011 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
opencli-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCLI Research
Use OpenCLI as an optional research-side plugin for structured retrieval.
OpenCLI is a CLI runtime, not an MCP server. Use it when the task maps cleanly to an existing OpenCLI adapter and the goal is to reduce model context size by retrieving stable structured output.
This skill follows the binding five-state model in optional-capabilities.md.
Preferred Tool Order
- Use OpenCLI when an existing adapter already matches the source and fields you need.
- Use MCP
fetchorimagefetchwhen the task is still web retrieval but OpenCLI is unavailable or not the right fit. - Use Playwright MCP or Chrome DevTools MCP when the task depends on interaction, rendered state, screenshots, or adapter debugging.
- Use workspace file and symbol tools for repo-local code understanding instead of forcing OpenCLI into the wrong lane.
Use Playwright MCP only after local-first and structured retrieval paths fail to answer the question, and retain reverse-checkable browser evidence when it is used.
Availability Check
Before using OpenCLI, verify it is installed:
opencli --version
- Exit code
0: OpenCLI is available. - Non-zero or command-not-found: OpenCLI is unavailable. Use the fallback strategy below.
Treat adapter or session setup gaps as available-but-needs-init. Treat unsupported sources or missing required fields as available-but-not-ready.
Fallback Strategy
If OpenCLI is unavailable or the required adapter cannot reach the needed data:
- If the target is a normal web page, fall back to MCP
fetchorimagefetch. - If the target requires page interaction, rendered state, screenshots, or network debugging, fall back to Playwright MCP or Chrome DevTools MCP.
- If the task is repo-local code understanding, use workspace file/symbol tools instead.
Do not silently pretend OpenCLI succeeded when it did not.
No-Tool Behavior
If neither OpenCLI nor the documented MCP or workspace fallback can satisfy the task, stop and say which capability is missing.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 99 lines · 55 tokens per session scan A cb1fe6069eea
opencli-research is a skill published in the GitHub repository monkey1wizard/Golem-Agents-Legion (15 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 938 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…