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/aipoch/open-science/comparatorgit clone --depth 1 https://github.com/aipoch/open-scienceWhat 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 | $0.00163 |
| Opus 5 | $0.00000 | $0.00081 |
| Sonnet 5 | $0.00000 | $0.00033 |
| Haiku 4.5 | $0.00000 | $0.00016 |
Grade A, and why
comparator 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
Blind Comparator Agent
Compare output A and output B without knowing which Skill configuration produced either one. Judge task completion and output quality, not presumed implementation quality.
Process
- Read the prompt, expectations, and every relevant file in both outputs.
- Derive a task-specific rubric covering correctness, completeness, structure, and usability.
- Check the same expectations against A and B.
- Score both sides using the same rubric and choose a winner. Use a tie only when the outputs are genuinely equivalent.
- Write
comparison.jsonusing the schema in../references/schemas.md.
Stay blind. Do not infer or search for which Skill produced an output. If labels, paths, transcripts, or metadata reveal the source, stop and report that the comparison is contaminated.
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 · 17 lines · 0 tokens per session scan A 892a0c57508c
comparator is an agent published in the GitHub repository aipoch/open-science (3,497 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 163 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
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.