coding-principles
Skill4 starsChanged 7 months agoMITView on GitHub
Core behavioral principles: when to ask, when to push back, when to simplify, how to make surgical changes
13 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- nesquena/steward-ostheir own version, first seen Nov 3, 2026
- a2ui-project/a2uitheir own version, first seen Nov 1, 2026
- hajdu-patrik/claude-workspacetheir own version, first seen Nov 1, 2026
- hajdu-patrik/triroutertheir own version, first seen Nov 1, 2026
- google/A2UItheir own version, first seen Oct 25, 2026
- paologum/claude-skillstheir own version, first seen Oct 25, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- kaustubhhiware/agent-skills-fullstack-development★ 1625% same
- sefaertunc/anthropic-watch★ 1100% same
Wrote their own version · 11
- a2ui-project/a2ui★ 17ksame name
- google/A2UI★ 17ksame name
- shinpr/claude-code-workflows★ 712same name
- nesquena/steward-os★ 76same name
- hajdu-patrik/claude-workspace★ 46same name
- hajdu-patrik/trirouter★ 46same name
- Ron-dali/vibe-coding-rules★ 4same name
- thejordanleopold/claude-code-skills-distilled★ 4same name
- aivos-xie/hermes-skills★ 1same name
- 10xequity/claude-skill-library★ 0same name
1 more not listed
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 repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-routingSkill
- backend-conventionsSkill
- claude-md-maintenanceSkill
- context-managementSkill
- coordinator-modeSkill
- frontend-design-systemSkill
- git-conventionsSkill
- memory-architectureSkill
- planning-with-filesSkill
- project-patternsSkill
- prompt-engineeringSkill
- review-and-handoffSkill
- security-checklistSkill
- subagent-usageSkill
- testingSkill
- verificationSkill
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 12 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
12
Distinctive
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 13
Don't assume. Don't hide confusion.
- Distinctive: line 16
If multiple interpretations exist, present them — don't pick silently.
- Distinctive: line 17
If a simpler approach exists, say so.
- Distinctive: line 18
If something is unclear, stop.
- Distinctive: line 26
No features beyond what was asked.
- Distinctive: line 28
No error handling for impossible scenarios.
- Distinctive: line 29
If you wrote 200 lines and it could be 50, rewrite it.
- Distinctive: line 31
When NOT to simplify: hot paths, stable legacy, framework boilerplate, security-critical code, code you don't fully understand.
- Distinctive: line 37
Don't "improve" adjacent code, comments, or formatting.
- Distinctive: line 38
Don't refactor things that aren't broken.
- Distinctive: line 40
Remove imports/variables YOUR changes made unused.
- Distinctive: line 41
Never combine cleanup with feature work.
“Common” is measured: kept by at least 6 in 10 of the 12 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
Coding Principles
Reference card. Depth and examples live in the linked skills — this file consolidates the rules, not the rationale.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
- State assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them — don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
See prompt-engineering/SKILL.md for eliciting quality and writing specs.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond what was asked. No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you wrote 200 lines and it could be 50, rewrite it.
When NOT to simplify: hot paths, stable legacy, framework boilerplate, security-critical code, code you don't fully understand. When in doubt, leave it — a working system is more valuable than a clean one. See the code-simplifier agent and /refactor-clean command.
3. Surgical Changes
Touch only what you must. Every changed line must trace to the request.
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- Remove imports/variables YOUR changes made unused. Leave pre-existing dead code unless asked.
- Never combine cleanup with feature work.
See git-conventions/SKILL.md for style matching and the /refactor-clean command for scope.
4. Goal-Driven Execution
Define success criteria up front. Loop until verified.
Transform tasks into verifiable goals:
- "Add validation" → "Write tests for invalid inputs, then make them pass"
- "Fix the bug" → "Write a failing test that reproduces it, then make it pass"
- "Refactor X" → "Ensure tests pass before and after"
Close the feedback loop BEFORE committing: change → verify → commit. Not: commit → discover it's broken.
See verification/SKILL.md, testing/SKILL.md, and planning-with-files/SKILL.md.
These principles are working if: fewer unnecessary diff lines, fewer rewrites from overcomplication, clarifying questions come before implementation rather than after mistakes.
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.

