follow-through
AGENTS.md0 starsChanged 3 months agoMITView on GitHub
Public Agent Skill and repository template for durable personal memory, ADR-style decisions, plans, reviews, and outcomes. profile: reviewed - Never copy personal records or Git history from a private repository into this project. - Never use real personal records as examples or test fixtures. Create explicitly labeled synthetic records. - Never weaken or bypass scripts/privacy_check.py to make a finding pass. - Never make bootstrap create a remote or push a user's private repository. - Never apply a schema update without…
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 repository3 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agentflowSkill
- follow-throughSkill
The file
We split this AGENTS.md into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Check publication boundary: python3 scripts/privacy_check.py
- Distinctive: line 21
Never copy personal records or Git history from a private repository into this project.
- Distinctive: line 23
Never use real personal records as examples or test fixtures.
- Very specific: line 25
Never weaken or bypass scripts/privacy_check.py to make a finding pass.
- Distinctive: line 26
Never make bootstrap create a remote or push a user's private repository.
- Distinctive: line 27
Never apply a schema update without first presenting its diff for explicit approval.
- Distinctive: line 29
Keep runtime code on the Python standard library unless a dependency is genuinely unavoidable and approved.
≈ “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
Follow Through
Public Agent Skill and repository template for durable personal memory, ADR-style decisions, plans, reviews, and outcomes.
profile: reviewed
Repo facts
- Install: none.
- Test:
python3 -m unittest discover -s tests -v - Validate example:
python3 scripts/validate.py examples/maya-chen - Check publication boundary:
python3 scripts/privacy_check.py - Development server: none.
- Skill and implementation:
SKILL.md,references/,scripts/,assets/ - Tests:
tests/ - Synthetic fixture:
examples/maya-chen/
Hazards
- Never copy personal records or Git history from a private repository into this project.
- Never use real personal records as examples or test fixtures. Create explicitly labeled synthetic records.
- Never weaken or bypass
scripts/privacy_check.pyto make a finding pass. - Never make bootstrap create a remote or push a user's private repository.
- Never apply a schema update without first presenting its diff for explicit approval.
- Keep runtime code on the Python standard library unless a dependency is genuinely unavoidable and approved.
- Preserve the two-commit synthetic lifecycle: its Git history is validator
coverage for
awaiting-outcometoreviewed.
ui-surfaces: none
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.