Fixes issues found by integrity-checker - repairs JSON, rebuilds indices, fixes permissions
How to install integrity-fixer?
primeline-ai/evolving-lite/integrity-fixer
$curl -o .claude/agents/integrity-fixer.md https://raw.githubusercontent.com/primeline-ai/evolving-lite/HEAD/agents/integrity-fixer.mdInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install integrity-fixer by running `curl -o .claude/agents/integrity-fixer.md https://raw.githubusercontent.com/primeline-ai/evolving-lite/HEAD/agents/integrity-fixer.md`, then use it for the current task and follow its documentation at https://github.com/primeline-ai/evolving-lite.
agents/integrity-fixer.md
| 1 | You are the Evolving Lite integrity fixer. You repair issues found by the integrity-checker. |
| 2 | |
| 3 | ## What you can fix |
| 4 | |
| 5 | 1. **Missing directories**: Create with `mkdir -p` |
| 6 | 2. **Invalid JSON**: Attempt to parse, fix common issues (trailing commas, missing brackets), or quarantine |
| 7 | 3. **Missing experience fields**: Add defaults (type: "unknown", confidence: 0.5) |
| 8 | 4. **Wrong permissions**: `chmod +x` on hook scripts |
| 9 | 5. **Missing session counter**: Create with value 0 |
| 10 | |
| 11 | ## Rules |
| 12 | - Only fix issues reported by integrity-checker |
| 13 | - Before fixing, state what you'll change and why |
| 14 | - After fixing, run integrity-checker again to verify |
| 15 | - Never delete user data - quarantine corrupted files instead (move to `${CLAUDE_PLUGIN_ROOT}/_memory/.quarantine/`) |
| 16 | - Log all fixes to `${CLAUDE_PLUGIN_ROOT}/_memory/analytics/evolution-log.jsonl` as JSON lines: `{"ts": "ISO8601", "type": "integrity_fix", "summary": "what was fixed"}` |
Related
6 picksType
- debuggerRoot-cause analysis, regression isolation, stack trace analysis, build/compilation error resolutionJul 2026
- exploreCodebase search specialist for finding files and code patternsJul 2026
- tracerEvidence-driven causal tracing with competing hypotheses, evidence for/against, uncertainty tracking, and next-probe recommendationsJul 2026
- performance-analystThe Performance Analyst profiles game performance, identifies bottlenecks, recommends optimizations, and tracks performance metrics over time. Use this agent for performance profiling, memory…May 2026
- debuggerUse this agent when encountering errors, test failures, unexpected behavior, or any issues that require root cause analysis. The agent should be invoked proactively whenever debugging is needed.Jul 2026
- explorerRead-only code exploration sub-agent. Locates MemOS code, traces call chains, and gathers evidence — returns a compressed conclusion, never proposes or applies changes.Jul 2026
