EvalHarness
AGENTS.md7 starsChanged 31 days agoMITView on GitHub
Before a task, check whether one of these skills applies and follow it when it matches the user's intent. The bundled model-finder MCP server provides read-only tools for these skills: modelfinder_audit_models, modelfinder_draft_eval_examples, modelfinder_create_eval_config, modelfinder_validate_eval_config, modelfinder_check_output, modelfinder_rank_eval_results, modelfinder_generate_routing, modelfinder_estimate_cost, modelfinder_estimate_memory and modelfinder_scan_sensitive_data. Prefer them over manual arithmetic or ad hoc scripts. If a tool says the project is unknown (Codex starts servers without a workspace), call it again with path set to the absolute path of the current project. These skills…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository4 other files it gives its agents.
- eval-modelsSkill
- find-modelSkill
- route-modelsSkill
- size-local-modelSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 3
Before a task, check whether one of these skills applies and follow it when it matches the user's intent.
- Very specific: line 6
eval-models: run the user's examples against candidate models and measure pass rate, latency, and cost.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Model Finder skills
Before a task, check whether one of these skills applies and follow it when it matches the user's intent.
- find-model: recommend AI models across providers for a task, budget, and route, including coding subtasks in an IDE. Read skills/find-model/SKILL.md.
- eval-models: run the user's examples against candidate models and measure pass rate, latency, and cost. Read skills/eval-models/SKILL.md.
- route-models: generate cheapest-first routing with quality guards and a LiteLLM config. Read skills/route-models/SKILL.md.
- size-local-model: estimate local memory for weights and KV cache. Read skills/size-local-model/SKILL.md.
The bundled model-finder MCP server provides read-only tools for these skills: modelfinder_audit_models, modelfinder_draft_eval_examples, modelfinder_create_eval_config, modelfinder_validate_eval_config, modelfinder_check_output, modelfinder_rank_eval_results, modelfinder_generate_routing, modelfinder_estimate_cost, modelfinder_estimate_memory and modelfinder_scan_sensitive_data. Prefer them over manual arithmetic or ad hoc scripts. If a tool says the project is unknown (Codex starts servers without a workspace), call it again with path set to the absolute path of the current project.
These skills are advisory. Never change the user's active model, deploy anything, or send data to a provider without explicit approval. API keys come only from environment variables.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.