decision-records
Skill0 starsChanged 37 days agoMITView on GitHub
Keep a project's shared knowledge where the second reader can reach it: a glossary with one term per concept and the words to avoid, decision records for choices that are hard to reverse and surprising without context, dated research documents that record what a source taught, all as tables with honest calibration, naming systems and roles but never people. Triggers on: "ADR", "decision record", "glossary", "define the term", "what do we call", "record the decision", "research doc", "write down what we learned", "where should this live", a term used in conflict with the glossary, output that contradicts an existing record.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- axodouble/skillstheir own version, first seen Nov 8, 2026
- zxyycom/skillstheir own version, first seen Nov 8, 2026
- musterd-io/musterdtheir own version, first seen Nov 1, 2026
- swestfall21/claude-skillstheir own version, first seen Oct 15, 2026
- theultimate-dev/skillstheir own version, first seen Oct 11, 2026
- skymavis/skillstheir own version, first seen Oct 11, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- kellervater/homeracker★ 562same name
- kellerlabs/homeracker★ 553same name
- markphelps/agent-plugins★ 6same name
- theultimate-dev/skills★ 2same name
- zxyycom/skills★ 2same name
- musterd-io/musterd★ 1same name
- skymavis/skills★ 1same name
- axodouble/skills★ 0same name
- swestfall21/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- cut-ticketsSkill
- deep-modulesSkill
- evidenceSkill
- grill-planSkill
- plain-voiceSkill
- plan-projectSkill
- review-changeSkill
- setup-conventionsSkill
- test-firstSkill
- thin-slicesSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
3
Distinctive
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 32
Create files lazily: a glossary when the first term is resolved, docs/adr/ when the first decision qualifies, a research document when a …
- Very specific: line 48
Before exploring an area, read GLOSSARY.md and the records under docs/adr/ that touch it.
- Distinctive: line 50
When a term conflicts with the glossary, say so at once: "The glossary defines cancellation as X.
- Distinctive: line 52
When a term is vague or overloaded, propose the canonical one.
- Distinctive: line 54
When a statement about how something works disagrees with the code, surface the contradiction.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Decision records
Three kinds of record, each with a format in references/:
| Record | Lives at | Format |
| Glossary | GLOSSARY.md at the root, or one per context listed in GLOSSARY-MAP.md | references/glossary-format.md |
| Decision record | docs/adr/NNNN-slug.md | references/adr-format.md |
| Research document | docs/research/<date>-<question>.md, or the path docs/agents/conventions.md names | references/research-document.md |
Create files lazily: a glossary when the first term is resolved, docs/adr/ when the first
decision qualifies, a research document when a source taught something.
The rules
| Id | Rule | In practice |
| DECIDE-1 | A record for a hard-to-reverse, surprising trade-off | All three must hold. Easy to reverse: you will just reverse it. Not surprising: nobody will wonder why. No real alternative: nothing to record. One paragraph is enough. |
| DECIDE-2 | Glossary terms are opinionated and implementation-free | One term per concept, the others under "avoid", one or two sentences on what it is. No implementation detail, no scratch notes, no specifications. |
| DECIDE-3 | Knowledge in tables with calibration | Glossaries, research documents and plan tables have fixed columns, in the repository, and every row's calibration is written (EVID-1): "unverified", never blank. The decision record is the prose exception, one paragraph. Prose elsewhere is for the reader who already has the table. |
| DECIDE-4 | Records carry no names | Systems and roles, never individuals. |
| DECIDE-5 | One file per topic, never another's file | Check the path before writing. A file not created in this session is not overwritten; a new dated document sits beside the earlier one. |
| DECIDE-6 | Conflicts with a record are surfaced | "Contradicts record 0003 (attribution patterns by default); worth reopening because …" rather than a silent override. |
During design
- Before exploring an area, read
GLOSSARY.mdand the records underdocs/adr/that touch it; the triggers for conflicts fire only on what was read. - When a term conflicts with the glossary, say so at once: "The glossary defines cancellation as X; this means Y. Which is it?"
- When a term is vague or overloaded, propose the canonical one.
- Stress-test relationships with concrete scenarios that probe the edges.
- When a statement about how something works disagrees with the code, surface the contradiction.
- Resolve a term, write it down then. Do not batch glossary updates.
What qualifies for a decision record
Architectural shape. Integration patterns between contexts. Technology choices with lock-in that would take a quarter to swap. Boundary and scope decisions, the explicit no as much as the yes. Deliberate deviations from the obvious path, so the next engineer does not "fix" them. Constraints not visible in the code. Rejected alternatives when the rejection is non-obvious.
Companion skills
| Need | Skill |
| The questions that surface the decisions | grill-plan |
| Calibration tags for the rows | evidence |
| The plan's Decisions table for reversible choices | plan-project |
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.

