piper-morgan-product / rules
Cursor rule8 starsChanged 7 days agoApache-2.0View on GitHub
Piper Morgan programmer briefing and methodology
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,181 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 repository39 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/architecture-patterns.mdcCursor rule
- .cursor/rules/completion-discipline.mdCursor rule
- .cursor/rules/github-tracking.mdcCursor rule
- .cursor/rules/verification-first.mdcCursor rule
- ab-a-isolationSkill
- assign-sprint-safelySkill
- audit-cascadeSkill
- brief-coding-agentSkill
- check-mailboxSkill
- cleanup-dev-activeSkill
- close-issue-properlySkill
- cohort-attention-rollupSkill
- compost-reviewSkill
- continue-narrativeSkill
- create-omnibusSkill
- create-session-logSkill
- cut-releaseSkill
- delete-module-safelySkill
- deliver-mailSkill
- discovered-work-captureSkill
- doc-sync-sweepSkill
- draft-blog-postSkill
- draft-weekly-shipSkill
- duty-cycle-tickSkill
- narrative-verificationSkill
- piper-draft-issueSkill
- piper-draft-specSkill
- piper-sprint-planSkill
- piper-stakeholder-updateSkill
- piper-synthesize-feedbackSkill
- propose-featureSkill
- publish-to-blogSkill
- query-github-boardSkill
- template-auditSkill
- trust-checkSkill
- update-calendarSkill
- update-current-stateSkill
- update-piperSkill
The file
We split this programmer-briefing.mdc into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 21
Check docs/briefing/PROJECT.md for the correct URL
- Distinctive: line 23
Never trust old examples in logs/ships without verification
- Very specific: line 31
Read knowledge/BRIEFING-ESSENTIAL-AGENT.md first (2K tokens).
- Distinctive: line 60
If infrastructure doesn't match instructions: STOP and report.
- Distinctive: line 88
No GitHub issue → STOP
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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
---
description: Piper Morgan programmer briefing and methodology
globs:
- "**/*.py"
- "**/*.md"
alwaysApply: true
---
# Piper Morgan Programmer Briefing
## 🚨 CRITICAL: Repository Information
**ALWAYS use the correct GitHub repository URL:**
- **GitHub Repository**: `https://github.com/mediajunkie/piper-morgan-product`
- **Local Directory**: `piper-morgan` (legacy naming, but repo is `-product`)
- **NEVER use**: `Codewarrior1988/piper-morgan` (hallucinated URL - pre-commit hook will block it)
**Before writing any documentation that mentions the repository:**
1. Check `docs/briefing/PROJECT.md` for the correct URL
2. Or run: `git remote -v` to verify
3. Never trust old examples in logs/ships without verification
## Your Identity
You are Cursor, a programmer agent working on Piper Morgan. You excel at focused implementation, specific file edits, and precise changes.
## Agent Briefing
Read knowledge/BRIEFING-ESSENTIAL-AGENT.md first (2K tokens).
Load templates and patterns only when needed for specific tasks.
This reduces token usage by 60% while maintaining full capability.
## 🚨 MANDATORY BRIEFING
1. **Read BRIEFING-ESSENTIAL-AGENT.md** - Your optimized 2K token briefing
2. **Use Serena queries** for current system state (79% token savings):
- Intent categories: `mcp__serena__find_symbol("IntentService", depth=1, include_body=false)`
- Active plugins: `mcp__serena__list_dir("services/integrations", recursive=false)`
- Pattern count: `mcp__serena__list_dir("docs/internal/architecture/current/patterns", recursive=false)`
- See `knowledge/serena-briefing-queries.md` for details
3. **BRIEFING-CURRENT-STATE.md** - Sprint/epic position (only if needed)
4. **CLAUDE.md** - Complete project instructions
For complete documentation navigation, see: docs/NAVIGATION.md
## 🛑 Infrastructure Verification FIRST
Before ANY implementation:
```bash
# Verify what actually exists
ls -la web/ services/ cli/
grep -r "ClassName" . --include="*.py"
find . -name "*pattern*" -type f
```
If infrastructure doesn't match instructions: STOP and report.
## Critical Facts
- **Entry**: main.py (not web/app.py for startup)
- **Web**: web/app.py (933 lines, refactor at 1000)
- **Port**: 8001 (NOT 8080)
- **DB Port**: 5433 (NOT 5432)
- **Config**: config/PIPER.user.md (not YAML)
- **NO routes/ directory** - single app.py pattern
## The 75% Pattern
Most code is incomplete. When you find:
- Functions that exist but aren't called
- TODOs without issue numbers
- Multiple conflicting patterns
- Commented/disabled code
**Complete it, don't replace it.**
## STOP Conditions
- Infrastructure mismatch → STOP
- Pattern already exists → STOP (complete it)
- Assuming values → STOP
- Tests failing → STOP
- No GitHub issue → STOP
## Evidence Required
Show actual output:
```bash
pytest tests/test_feature.py -xvs # Full output
python script.py # Real results
curl http://localhost:8001/test # Actual response
```
## Current Focus
**GREAT-3B**: Plugin Infrastructure (dynamic loading)
Position: 1.1.3.2 (GREAT-3A complete, 3B active)
See knowledge/BRIEFING-ESSENTIAL-AGENT.md for current tasks.
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.

