minimal-implementation
Skill3 starsChanged 44 days agoApache-2.0View on GitHub
Run before implementation to record minimal necessary approach using Harness Decision Ladder.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- zxyycom/skillstheir own version, first seen Nov 8, 2026
- ooooooooooooooooooop/agent-toolstheir own version, first seen Oct 22, 2026
- ooooooooooooooooooop/personal-aitheir own version, first seen Oct 22, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- ooooooooooooooooooop/agent-tools★ 4same name
- ooooooooooooooooooop/personal-ai★ 4same name
- zxyycom/skills★ 2same 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 repository10 other files it gives its agents.
- engineering-harnessSkill
- adversarial-reviewSkill
- collect-evidenceSkill
- complexity-reviewerSkill
- convergenceSkill
- diagnosability-reviewSkill
- engineering-harnessSkill
- quality-gateSkill
- reproduce-findingSkill
- task-contractSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 1 is distinctive, and 5 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.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Run in PLANNED, before IMPLEMENTING.
- Very specific: line 11
Read .harness/current-task.yaml, requirements, invariants, design/plan, and dependency manifest.
- Distinctive: line 19
Only then choose new abstraction.
- Very specific: line 21
Search repository before creation.
- Very specific: line 23
Write YAML matching schemas/minimal-implementation.schema.json, then run:
- Very specific: line 29
Do not transition to IMPLEMENTING until command succeeds.
≈ “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
Minimal Implementation Check
Run in PLANNED, before IMPLEMENTING. Do not implement code.
Read .harness/current-task.yaml, requirements, invariants, design/plan, and dependency manifest. Answer ladder in order:
- Does capability need to exist?
- Does equivalent repository capability exist?
- Can stdlib solve it?
- Can platform-native capability solve it?
- Can installed dependency solve it?
- Can small local implementation solve it?
- Only then choose new abstraction.
Search repository before creation. First found short-circuits later checks: write checked: false, result: skipped. Requirement/invariant-required security, audit, compatibility, migration, accessibility, NFR, and trust-boundary complexity remains necessary.
Write YAML matching schemas/minimal-implementation.schema.json, then run:
harness check minimal --file /path/to/decision.yamlDo not transition to IMPLEMENTING until command succeeds.
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.