ynoslop
AGENTS.md0 starsChanged 3 months agoMITView on GitHub
Eval bench measuring what agent skills do to model output: one prompt, run twice per model (bare / skilled), compared by deterministic metrics and blind LLM judges. README.md is the current reference for the pipeline, file formats, freshness and isolation — read it first. - bin/run and bin/judge spend real money on the local CLI credentials. Never invoke them casually. bin/collect and bin/results are offline and free. - Never hand-edit evals/*/runs/. Machine-written recordings; treat overwriting one as destroying data that…
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 31,542 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 repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- Attention-kindSkill
- RundownSkill
- SpartanSkill
- humanizerSkill
- no-slop-writingSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
A pair must differ only by the skill: Don't add instruction text anywhere a spawned CLI could pick it up — see "Isolation" in the README.
≈ “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
ynoslop — agents guide
Eval bench measuring what agent skills do to model output: one prompt, run
twice per model (bare / skilled), compared by deterministic metrics and blind
LLM judges. README.md is the current reference for the pipeline, file
formats, freshness and isolation — read it first.
Working here
bin/runandbin/judgespend real money on the local CLI credentials. Never invoke them casually.bin/collectandbin/resultsare offline and free.- Never hand-edit
evals/*/runs/. Machine-written recordings; treat overwriting one as destroying data that costs money to reproduce. - A pair must differ only by the skill. Don't add instruction text anywhere a spawned CLI could pick it up — see "Isolation" in the README.
bunx tsc --noEmit(make typecheck) must pass. There are no tests.PRD.mdandDESIGN.mddescribe the removed v1 static site (public/). They are kept for the problem statement and decision history; never implement from them.
Part of the ynfra monorepo, split to git@github.com:ynfra/ynoslop.git
via Copybara. Commits use the [ynoslop] message convention from the root
AGENTS.md.
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.