Gridline
AGENTS.md39 starsChanged 23 days agoMITView on GitHub
This repository maintains portable architecture/AEC Agent Skills and provider adapters.
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 repository31 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- architectural-drawing-generationSkill
- architecture-orchestratorSkill
- architecture-programmingSkill
- architecture-red-teamSkill
- area-quantity-auditSkill
- autocad-dwg-workflowSkill
- building-envelope-performanceSkill
- cad-bim-automationSkill
- civil-site-designSkill
- concept-design-reviewSkill
- concept-schematic-designSkill
- construction-administrationSkill
- construction-documentationSkill
- cost-planning-value-engineeringSkill
- drawing-qaSkill
- handover-fm-postoccupancySkill
- interior-fitout-designSkill
- life-safety-accessibilitySkill
- materials-specificationsSkill
- mep-coordinationSkill
- openbim-ifc-coordinationSkill
- precedent-researchSkill
- presentation-reviewSkill
- revit-workflowSkill
- rhino-grasshopper-workflowSkill
- site-analysis-feasibilitySkill
- site-regulation-researchSkill
- structural-coordinationSkill
- sustainability-daylight-energySkill
- visualization-renderingSkill
The file
We split this AGENTS.md into the rules it gives an agent
8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 6
Keep canonical portable skills in skills/<name>/SKILL.md.
- Distinctive: line 7
Keep provider-specific behavior thin.
- Distinctive: line 8
Treat token/context efficiency as a feature.
- Distinctive: line 10
Never claim architectural, planning, structural, fire, accessibility, legal, or construction compliance without authoritative evidence and …
- Distinctive: line 11
Verify provider formats against current official documentation before changing manifests, install locations, or agent schemas.
- Very specific: line 12
Keep Claude plugin skill copies synchronized with canonical skills/.
- Distinctive: line 13
Prefer additive, backward-compatible changes.
- Very specific: line 14
Run python3 tests/check_repo.py and python3 -m unittest discover -s tests -v before committing repository changes.
≈ “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
Repository Agent Instructions
This repository maintains portable architecture/AEC Agent Skills and provider adapters.
Priorities
- Keep canonical portable skills in
skills/<name>/SKILL.md. - Keep provider-specific behavior thin; do not fork domain logic unnecessarily.
- Treat token/context efficiency as a feature.
- Preserve beginner-first installation paths and documentation.
- Never claim architectural, planning, structural, fire, accessibility, legal, or construction compliance without authoritative evidence and appropriate human review.
- Verify provider formats against current official documentation before changing manifests, install locations, or agent schemas.
- Keep Claude plugin skill copies synchronized with canonical
skills/; CI must fail on drift. - Prefer additive, backward-compatible changes.
- Run
python3 tests/check_repo.pyandpython3 -m unittest discover -s tests -vbefore committing repository changes.
Release discipline
For substantial changes, update CHANGELOG.md and relevant docs. Keep versions synchronized across provider manifests.
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.

