clickhouse-sink-connector
CLAUDE.md345 starsChanged 35 days agoApache-2.0View on GitHub
Read AGENTS.md before making any change to this repository. This repository operates strictly under Spec-Driven Development (SDD): - Spec First: Every agentic change to the code must first declare the specification in specs/ and implement exactly what was declared. - Smart Ralph Protocol: Follow the agentic workflow rules in specs/SMART_RALPH_PROTOCOL.md and specs/CONSTITUTION.md. - Formal Verification: Ensure changes align with the Lean 4 formal verification proofs in formal_specs/lean/. - Validation: Always run python3 scripts/validate_specs.py before proposing code changes. It carries the…
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- clickhouse-sink-reviewSkill
- code-quality-architectureSkill
- code-quality-bashSkill
- code-quality-goSkill
- code-quality-jvmSkill
- code-quality-pythonSkill
- code-quality-sqlSkill
- code-reuse-firstSkill
- code-reuse-reviewSkill
- design-note-debtSkill
- destructive-operation-safetySkill
- mandatory-code-change-validationSkill
- pr-self-reviewSkill
- repro-harness-negative-proofSkill
- sink-connector-mysql-source-of-truthSkill
The file
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 3
Read AGENTS.md before making any change to this repository.
- Very specific: line 6
Spec First: Every agentic change to the code must first declare the specification in specs/ and implement exactly what was declared.
- Very specific: line 7
Smart Ralph Protocol: Follow the agentic workflow rules in specs/SMART_RALPH_PROTOCOL.md and specs/CONSTITUTION.md.
- Very specific: line 8
Formal Verification: Ensure changes align with the Lean 4 formal verification proofs in formal_specs/lean/.
- Very specific: line 9
Validation: Always run python3 scripts/validate_specs.py before proposing code changes.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md
Read AGENTS.md before making any change to this repository.
This repository operates strictly under Spec-Driven Development (SDD):
- Spec First: Every agentic change to the code must first declare the specification in
specs/and implement exactly what was declared. - Smart Ralph Protocol: Follow the agentic workflow rules in
specs/SMART_RALPH_PROTOCOL.mdandspecs/CONSTITUTION.md. - Formal Verification: Ensure changes align with the Lean 4 formal verification proofs in
formal_specs/lean/. - Validation: Always run
python3 scripts/validate_specs.pybefore proposing code changes.
It carries the prime directive for this codebase, which decides most design questions here:
This project is a replication engine from a transactional source database (MySQL, PostgreSQL) into ClickHouse. The source data is the truth and the source is always correct. The ClickHouse side must conform to the source, and every mismatch is fixed by making ClickHouse match the source — always.
Two rules from it that are wrong most often, so they are repeated here:
- ALIAS columns: ignore them. Not stored, so nothing can diverge.
- MATERIALIZED columns: these are stored, computed by ClickHouse. If the source also defines a column of that name, the replica silently holds ClickHouse's derived value instead of the source's — no error, matching row counts. That is a real divergence, and the remediation is on the ClickHouse side.
AGENTS.md also covers the fail-loudly rules, the value-level verification requirement (row counts are not proof), and the repository layout.
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.