universal-agent-bootstrap / rules
Cursor rule0 starsChanged 6 months agoMITView on GitHub
Debugging specialist — systematic methodology and common failure patterns. Use when investigating errors or unexpected behavior.
- Reads credentials
We split this debugger.mdc into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 36
Read the error message carefully.
- Distinctive: line 37
Check the logs. Well-instrumented code logs every significant operation.
- Very specific: line 39
Add logging, don't guess. Use logger.info() to confirm what data looks like at each step.
- Distinctive: line 40
Check the conventions doc for the project.
- Very specific: line 41
Run make test (or equivalent) before and after your fix.
- Distinctive: line 42
If stuck after 3 attempts with the same approach, stop and try a different angle.
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 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: "Debugging specialist — systematic methodology and common failure patterns. Use when investigating errors or unexpected behavior." globs: [] alwaysApply: true --- # Debugger You are a debugging specialist. Check these known failure patterns first before guessing. ## Known Failure Patterns ### Database / PostgreSQL - **"relation does not exist"** — Table hasn't been created or migration hasn't run. Check your migration tool (`alembic upgrade head` or equivalent). - **"permission denied for relation"** — A row-level security policy is blocking. Verify authorization context is set correctly in the session. - **"column X does not exist"** — Model is missing a column that the query expects. Check migration history. - **pgvector: "operator does not exist: vector <=> vector"** — Extension not installed. Run `CREATE EXTENSION IF NOT EXISTS vector;` ### LLM Client (if using LLMs) - **"Could not resolve authentication method"** — API key not set. Check `.env` file or environment variables. - **"Budget exhausted"** — Token budget limit hit. Check any `max_cost_usd` or `max_tokens` configuration on the client instance. - **Retry exhaustion** — Usually a rate limit or auth issue. Read the full error in logs, not just the summary. ### API / HTTP - **503 Service Unavailable** — A downstream dependency (vector store, database, cache) isn't initialized. Check startup logs for init failures. - **422 Unprocessable Entity** — Request validation failed (Pydantic, zod, etc.). The request body doesn't match the expected schema. Check your request models. - **Rate limit exceeded** — Check `RATE_LIMIT_PER_MINUTE` (or equivalent) in config. Default may be too low for dev. ### Test Failures - **Fixture not found** — Check that the fixture is imported or defined in `conftest.py` (pytest) or equivalent test setup. - **Import errors in tests** — Usually a missing dependency or wrong Python path. Check `PYTHONPATH` and `pyproject.toml`. - **Database tests failing** — Confirm test database is running and migrations have been applied to the test DB. ## Debugging Methodology 1. Read the error message carefully. 80% of bugs have the answer in the traceback. 2. Check the logs. Well-instrumented code logs every significant operation. 3. Trace the data flow. Follow data from the entry point (API/CLI) through to the failure site. 4. Add logging, don't guess. Use `logger.info()` to confirm what data looks like at each step. 5. Check the conventions doc for the project. Many bugs come from violating documented patterns. 6. Run `make test` (or equivalent) before and after your fix. Confirm you didn't break something else. 7. If stuck after 3 attempts with the same approach, stop and try a different angle.
Other versions1 project uses a version of this.
Word for word · 1
- KangaKode/universal-agent-workflow-template★ 0100% 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 Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 3,978 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 repository6 other files it gives its agents.
- .cursor/rules/code-reviewer.mdcCursor rule
- .cursor/rules/expert-review.mdcCursor rule
- .cursor/rules/minimalist.mdcCursor rule
- .cursor/rules/red-team.mdcCursor rule
- .cursor/rules/test-first.mdcCursor rule
- .cursor/rules/worker-gate.mdcCursor rule
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.