Install
$ agentstack add skill-anthroos-claude-code-orchestrator-project-notes ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Project Notes
> Maintain a persistent knowledge base about the project. Claude reads this at the start of relevant tasks to have context without you re-explaining.
When to use
- "Remember that we use Postgres, not MySQL"
- "What do we know about the auth system?"
- "Add this to project notes"
- "What conventions do we follow?"
- When starting work on a project area you haven't touched in a while
Paths
| What | Path | |------|------| | Notes directory | $PROJECT_ROOT/notes/ | | Architecture notes | $PROJECT_ROOT/notes/architecture.md | | Conventions | $PROJECT_ROOT/notes/conventions.md | | Decisions log | $PROJECT_ROOT/notes/decisions.md |
How to execute
Reading notes
# List all notes
ls $PROJECT_ROOT/notes/
# Read specific topic
cat $PROJECT_ROOT/notes/architecture.md
Adding a note
Append to the appropriate file, or create a new topic file:
## [Topic] (YYYY-MM-DD)
**Decision:** [What was decided]
**Context:** [Why this decision was made]
**Alternatives considered:** [What else was considered]
Note categories
| File | What goes here | |------|---------------| | architecture.md | System design, service boundaries, data flow | | conventions.md | Naming, file structure, coding standards | | decisions.md | ADRs — why we chose X over Y | | integrations.md | External services, API keys location, endpoints | | troubleshooting.md | Known issues and their fixes |
Examples
Adding a decision
## Use Redis for caching (2024-03-15)
**Decision:** Use Redis instead of in-memory caching
**Context:** App runs on multiple instances, need shared cache
**Alternatives:** Memcached (less features), in-memory (no sharing)
Adding a convention
## API Response Format
All API endpoints return:
\```json
{
"data": {...},
"error": null,
"meta": {"timestamp": "...", "request_id": "..."}
}
\```
Tips
- Keep notes concise — bullet points over paragraphs
- Include dates — context changes over time
- Link to code —
src/auth/middleware.ts:45is better than "the auth middleware" - Delete outdated notes — stale context is worse than no context
Related skills
daily-summary— uses project notes for context
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: anthroos
- Source: anthroos/claude-code-orchestrator
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.