Claude-Code-Workflow
AGENTS.md2.1k starsChanged 7 months agoMITArchived repositoryView on GitHub
Incremental Progress: - Small, testable changes - Commit working code frequently - Build on previous work (subtasks) Evidence-Based: - Study 3+ similar patterns before implementing - Match project style exactly - Verify with existing code Pragmatic: - Boring solutions over clever code - Simple over complex - Adapt to project reality Context Continuity (Multi-Task): - Leverage resume for consistency - Maintain established patterns - Test integration between subtasks Git Operations (Parallel Task Safety): - Only stage/commit files directly produced by…
1 other project uses a version of this.
Adopted by
Most recently taken up by
- zhao-wuyan/ccw-command-explorerword for word, first seen May 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- zhao-wuyan/ccw-command-explorer★ 45100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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.
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 31,542 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 repository59 other files it gives its agents.
- brainstormSkill
- ccw-chainSkill
- ccw-helpSkill
- delegation-checkSkill
- investigateSkill
- issue-manageSkill
- memory-captureSkill
- memory-manageSkill
- prompt-generatorSkill
- review-codeSkill
- review-cycleSkill
- security-auditSkill
- shipSkill
- skill-generatorSkill
- skill-iter-tuneSkill
- skill-simplifySkill
- skill-tuningSkill
- spec-generatorSkill
- team-arch-optSkill
- team-brainstormSkill
- team-coordinateSkill
- team-designerSkill
- team-executorSkill
- team-frontend-debugSkill
- team-frontendSkill
- team-interactive-craftSkill
- team-issueSkill
- team-lifecycle-v4Skill
- team-motion-designSkill
- team-perf-optSkill
- team-planexSkill
- team-quality-assuranceSkill
- team-reviewSkill
- team-roadmap-devSkill
- team-tech-debtSkill
- team-testingSkill
- team-uidesignSkill
- team-ui-polishSkill
- team-ultra-analyzeSkill
- team-ux-improveSkill
- team-visual-a11ySkill
- wf-composerSkill
- wf-playerSkill
- workflow-executeSkill
- workflow-lite-executeSkill
- workflow-lite-planSkill
- workflow-lite-test-reviewSkill
- workflow-multi-cli-planSkill
- workflow-planSkill
- workflow-skill-designerSkill
- workflow-tdd-plan-planSkill
- workflow-test-fixSkill
- brainstormSkill
- investigateSkill
- review-cycleSkill
- spec-generatorSkill
- workflow-planSkill
- workflow-tdd-planSkill
- workflow-test-fixSkill
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
22 rules. About 0 are common, 15 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈15
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Follow project's existing patterns
- Distinctive: line 14
Test all public functions
- Distinctive: line 15
Test edge cases and error conditions
- Distinctive: line 23
Don't expose sensitive info
- Distinctive: line 29
Commit working code frequently
- Distinctive: line 35
Verify with existing code
- Distinctive: line 45
Test integration between subtasks
- Distinctive: line 48
Only stage/commit files directly produced by current task
- Distinctive: line 49
Never touch unrelated changes or other task outputs
- Very specific: line 50
Use git add <specific-files> instead of git add .
- Distinctive: line 51
Verify staged files before commit to avoid cross-task conflicts
- Distinctive: line 54
If your task conflicts with existing uncommitted changes, STOP and report the conflict instead of overwriting
- Distinctive: line 55
Treat all pre-existing uncommitted changes as intentional work-in-progress by other tools
- Very specific: line 60
Direct Binary Calls: Always call binaries directly in functions.shell, set workdir, avoid shell wrappers (bash -lc, cmd /c, etc.)
- Very specific: line 63
Use apply_patch tool for all routine text edits
- Distinctive: line 65
Avoid Python editing scripts unless both fail
- Distinctive: line 89
Use for: finding implementations, understanding architecture, locating patterns
- Very specific: line 93
Use smart_search(query="...") for keyword/regex search
- Very specific: line 94
Use smart_search(action="find_files", pattern="*.ts") for file discovery
- Very specific: line 98
Read multiple files in parallel: read_file(path="file1.ts"), read_file(path="file2.ts")
- Very specific: line 106
NEVER: use shell commands (cat, find, grep) when MCP tools are available.
- Distinctive: line 119
Before starting work, scan recent sessions (7 days) to avoid conflicts and reuse prior work:
≈ “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
Codex Code Guidelines
Code Quality Standards
Code Quality
- Follow project's existing patterns
- Match import style and naming conventions
- Single responsibility per function/class
- DRY (Don't Repeat Yourself)
- YAGNI (You Aren't Gonna Need It)
Testing
- Test all public functions
- Test edge cases and error conditions
- Mock external dependencies
- Target 80%+ coverage
Error Handling
- Proper try-catch blocks
- Clear error messages
- Graceful degradation
- Don't expose sensitive info
Core Principles
Incremental Progress:
- Small, testable changes
- Commit working code frequently
- Build on previous work (subtasks)
Evidence-Based:
- Study 3+ similar patterns before implementing
- Match project style exactly
- Verify with existing code
Pragmatic:
- Boring solutions over clever code
- Simple over complex
- Adapt to project reality
Context Continuity (Multi-Task):
- Leverage resume for consistency
- Maintain established patterns
- Test integration between subtasks
Git Operations (Parallel Task Safety):
- Only stage/commit files directly produced by current task
- Never touch unrelated changes or other task outputs
- Use
git add <specific-files>instead ofgit add . - Verify staged files before commit to avoid cross-task conflicts
Multi-CLI Coexistence (CRITICAL):
- If your task conflicts with existing uncommitted changes, STOP and report the conflict instead of overwriting
- Treat all pre-existing uncommitted changes as intentional work-in-progress by other tools
System Optimization
Direct Binary Calls: Always call binaries directly in functions.shell, set workdir, avoid shell wrappers (bash -lc, cmd /c, etc.)
Text Editing Priority:
- Use
apply_patchtool for all routine text edits - Fall back to
sedfor single-line substitutions if unavailable - Avoid Python editing scripts unless both fail
apply_patch invocation:
{
"command": ["apply_patch", "*** Begin Patch\n*** Update File: path/to/file\n@@\n- old\n+ new\n*** End Patch\n"],
"workdir": "<workdir>",
"justification": "Brief reason"
}Windows UTF-8 Encoding (before commands):
[Console]::InputEncoding = [Text.UTF8Encoding]::new($false)
[Console]::OutputEncoding = [Text.UTF8Encoding]::new($false)
chcp 65001 > $nullContext Acquisition (MCP Tools Priority)
For task context gathering and analysis, ALWAYS prefer MCP tools:
- mcp__ace-tool__search_context - HIGHEST PRIORITY for code discovery
- Semantic search with real-time codebase index
- Use for: finding implementations, understanding architecture, locating patterns
- Example:
mcp__ace-tool__search_context(project_root_path="/path", query="authentication logic")
- smart_search - Fallback for structured search
- Use
smart_search(query="...")for keyword/regex search - Use
smart_search(action="find_files", pattern="*.ts")for file discovery - Supports modes:
auto,hybrid,exact,ripgrep
- Use
- read_file - Batch file reading
- Read multiple files in parallel:
read_file(path="file1.ts"),read_file(path="file2.ts") - Supports glob patterns:
read_file(path="src/**/*.config.ts")
- Read multiple files in parallel:
Priority Order:
ACE search_context (semantic) → smart_search (structured) → read_file (batch read) → shell commands (fallback)NEVER use shell commands (cat, find, grep) when MCP tools are available.
Workflow Session Awareness
| Workflow | Directory | Summary File |
workflow-plan | .workflow/active/WFS-*/ | workflow-session.json |
workflow-lite-plan | .workflow/.lite-plan/{date}-{slug}/ | plan.json |
analyze-with-file | .workflow/.analysis/ANL-*/ | conclusions.json |
multi-cli-plan | .workflow/.multi-cli-plan/*/ | session-state.json |
lite-fix | .workflow/.lite-fix/*/ | fix-plan.json |
| Other | .workflow/.debug/, .workflow/.scratchpad/, .workflow/archives/ | — |
Before starting work, scan recent sessions (7 days) to avoid conflicts and reuse prior work:
- Overlapping file scope → warn, suggest referencing prior session
- Complementary findings → feed into current task context
Execution Checklist
Before:
- Understand PURPOSE and TASK clearly
- Use ACE search_context first, fallback to smart_search for discovery
- Use read_file to batch read context files, find 3+ patterns
- Check RULES templates and constraints
During:
- Follow existing patterns exactly
- Write tests alongside code
- Run tests after every change
- Commit working code incrementally
After:
- All tests pass
- Coverage meets target
- Build succeeds
- All EXPECTED deliverables met
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.

