dokion / frontend
AGENTS.md1 starsChanged 3 months agoMITView on GitHub
If any of these are missing from DESIGN.md, update DESIGN.md first or stop for review.
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 31,774 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 repository67 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- autoresearchSkill
- brainstormingSkill
- brandkitSkill
- create-github-action-workflow-specificationSkill
- design-taste-frontendSkill
- design-taste-frontend-v1Skill
- dispatching-parallel-agentsSkill
- dokion-hardeningSkill
- dokion-playbook-creatorSkill
- dokion-playbook-hubSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- full-output-enforcementSkill
- git-commitSkill
- github-publishing-workflowSkill
- google-ai-studio-web-editorSkill
- gpt-tasteSkill
- high-end-visual-designSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- industrial-brutalist-uiSkill
- minimalist-uiSkill
- receiving-code-reviewSkill
- redesign-existing-projectsSkill
- requesting-code-reviewSkill
- stitch-design-tasteSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- ui-ux-design-engineSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- writing-plansSkill
- writing-skillsSkill
- autoresearchSkill
- dokion-playbook-creatorSkill
- dokion-playbook-hubSkill
- dokion-hardeningSkill
- agent-playbookSkill
- archifySkill
- autoresearchSkill
- brainstormingSkill
- dispatching-parallel-agentsSkill
- dokion-automationSkill
- dokion-fullstackSkill
- dokion-hardeningSkill
- dokion-playbook-creatorSkill
- dokion-playbook-hubSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- github-publishing-workflowSkill
- google-ai-studio-web-editorSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- The first 60 shown.
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
15 rules. About 1 is common, 12 are distinctive, and 2 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈12
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 4
Before coding, inspect PRODUCT.md, DESIGN.md, package.json, routing files, component structure, and any existing tests.
- Distinctive: line 7
When encountering errors or bugs, the agent must enter Root Cause Mode:
- Distinctive: line 10
Avoid trial-and-error workarounds or surface-level patches.
- Very specific: line 13
Install Agent Harness: Ensure package dependencies and scripts are validated before making changes.
- Distinctive: line 14
Bulk Install Guard: Do not bulk-install every skill or harness blindly.
- Distinctive: line 15
React Harness Recommendation: Use a react error boundary and runtime boundary safety harness, strict TypeScript types, and standard hooks …
- Distinctive: line 25
If any of these are missing from DESIGN.md, update DESIGN.md first or stop for review.
- Distinctive: line 28
Do not delete existing features.
- Distinctive: line 29
Do not rename public routes or exported APIs without explicit approval.
- Distinctive: line 30
Do not replace the design system with unrelated styling.
- Common: line 33
Never expose API keys or secrets in client-facing code.
- Distinctive: line 34
If handling tokens, ensure they are masked in UI and not logged to the console.
- Distinctive: line 39
Check git diff before finalizing.
- Distinctive: line 40
Add or update tests when behavior changes.
- Distinctive: line 53
Stop and ask for review when a change requires:
≈ “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
Agent Instructions
Read This First
Before coding, inspect PRODUCT.md, DESIGN.md, package.json, routing files, component structure, and any existing tests. Do not rush to implementation without understanding the existing architecture.
Root Cause Mode
When encountering errors or bugs, the agent must enter Root Cause Mode:
- Perform root cause analysis before applying fixes.
- Identify exact file, line, and systemic cause.
- Avoid trial-and-error workarounds or surface-level patches.
Agent Harness Inventory & Setup
- Install Agent Harness: Ensure package dependencies and scripts are validated before making changes. Run
bun installor package audits when necessary. - Bulk Install Guard: Do not bulk-install every skill or harness blindly. Only install specific tools required for the task.
- React Harness Recommendation: Use a react error boundary and runtime boundary safety harness, strict TypeScript types, and standard hooks to guarantee runtime safety.
- Code Review Harness Recommendation: Perform a repository graph review and duplication scan across files before finalizing changes to prevent code bloat and regressions.
Design Read and Taste Check
Before implementation, restate:
- The page kind and audience.
- The chosen visual language.
- DESIGN_VARIANCE, MOTION_INTENSITY, and VISUAL_DENSITY.
- The design-system decision.
If any of these are missing from DESIGN.md, update DESIGN.md first or stop for review.
What Not To Change
- Do not delete existing features.
- Do not rename public routes or exported APIs without explicit approval.
- Do not replace the design system with unrelated styling.
Security & API Key Guidelines
- Never expose API keys or secrets in client-facing code.
- If handling tokens, ensure they are masked in UI and not logged to the console.
Regression Guard
- Preserve existing behavior.
- Limit changes to the requested scope.
- Check git diff before finalizing.
- Add or update tests when behavior changes.
Verification Checklist (MANDATORY)
You MUST complete these steps and provide proof before considering the task done.
- App builds successfully.
- Main flows still work.
- Mobile layout checked with no horizontal overflow and proper dynamic viewport units.
- Keyboard navigation checked with Tab, Enter, Space, and Escape.
- Loading, empty, and error states implemented.
- Run npx unslop-preflight audit in the terminal.
- Paste the final score and ensure there are 0 Errors before you complete the task. Do NOT skip this step.
When To Stop
Stop and ask for review when a change requires:
- Deleting core features.
- Changing data models or schemas.
- Altering auth/security behavior.
- Making broad redesign decisions.
Visual & Mobile QA Checklist
- No horizontal scrolling on mobile.
- Tap targets are at least 44x44px for touch devices.
- Color contrast passes mathematical deltas.
- All forms have explicit validation boundaries and error messages.
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.