run-economics
Skill100 starsChanged 4 months agoMITView on GitHub
Use when choosing between cheap probes, worker runs, expensive ruler runs, or long keepalive waits.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- codex-dispatchSkill
- fable-orchestrator-routerSkill
- public-readme-polisherSkill
- public-repo-operationalizerSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use cheap probes when the question is "does this mechanism fire?"
- Distinctive: line 23
Use premium runs when the question is "does this meet the bar?"
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
Run Economics
Match the instrument to the question.
Mechanism
Use cheap probes when the question is "does this mechanism fire?"
Examples:
- hook blocks stale wait
- cue reaches worker
- small parser case passes
- one narrow acceptance test catches the bug
Ruler
Use premium runs when the question is "does this meet the bar?"
Examples:
- release readiness
- final quality score
- customer-facing proof
- hard architectural judgment
Cache
For short waits, preserve the prompt cache with a sleep-tick if no inline work remains. For long waits, let the cache die once. Do not ping through multi-hour idle windows by default.
Ledger
For scored or judged runs, record provider, model or lane, scenario, method, score, and proof boundary.
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.