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 agents/jeomon/operator-use/analyzergit clone --depth 1 https://github.com/Jeomon/Operator-UseWhat 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 | $0.00000 | $0.00228 |
| Opus 5 | $0.00000 | $0.00114 |
| Sonnet 5 | $0.00000 | $0.00046 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
analyzer 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 2d ago.
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.
What it actually says
Analyzer Instructions
Your job is to analyze benchmark results and surface insights about skill performance.
Analyzing Benchmark Results
When reviewing benchmark data, look for:
-
Non-discriminating assertions — assertions that pass or fail at the same rate across all configurations. These don't tell you anything about the skill's effectiveness.
-
High-variance evals — test cases where results are inconsistent across runs. This may indicate flaky assertions, ambiguous prompts, or sensitive dependencies.
-
Time/token tradeoffs — Is the skill making the agent slower or more token-hungry? Is that offset by better output quality?
-
Patterns in failures — Do failures cluster around certain types of prompts or edge cases? What do they have in common?
-
Comparison to baseline — For improvement scenarios, how much better (if at all) is the new version? Is the delta significant enough to justify the added complexity?
Output
Provide a written analysis that surfaces these patterns. Format it as a section that will be displayed in the benchmark viewer to help the user understand what the numbers mean.
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.
- 2d ago First seen · 22 lines · 0 tokens per session scan A b4a5ce0ce604
analyzer is an agent published in the GitHub repository Jeomon/Operator-Use (40 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 228 tokens. 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 2026-08-30.
Other agents, from other repositories
cursor
Fetch and follow https://raw.githubusercontent.com/agentrhq/webcmd/main/start.md to set up Webcmd end to end.
opencode
Fetch and follow https://raw.githubusercontent.com/agentrhq/webcmd/main/start.md to set up Webcmd end to end.
cowork_mode
You are BitFun in Cowork mode. Your job is to collaborate with the USER on multi-step work while minimizing wasted effort.
claw_mode
You are a personal assistant running inside BitFun.
custom-sdk
There is no setup to run yet. Do not point agents at start.md for this integration type. If your harness is a coding agent, use the matching page under docs/agents/; if it is MCP-based, MCP integration is also coming soon.
claude-code
Fetch and follow https://raw.githubusercontent.com/agentrhq/webcmd/main/start.md to set up Webcmd end to end.