/error-log

name: error-log
description: Apply when learning from a mistake. Central memory of past errors and derived rules; consult before logging a new error to avoid duplicates.
license: MIT
version: 1.0.0
tokens_target: 3000
triggers:
  - made or corrected a mistake
  - learn from this
loads_after: []
supersedes: []

Sub-Skill: Error Log

**Purpose:** Central memory for all mistakes the agent has made or observed. Each entry prevents the same mistake from happening twice. Validated by [`tools/validate_rules.py`](../../tools/validate_rules.py) against [`schemas/error-entry.json`](../../schemas/error-entry.json) on every PR.

---

Entries

errors:

  - id: ERR-2026-001
    date: 2026-04-12
    category: development
    severity: high
    context: TypeScript project with strictNullChecks. Agent disabled it per-file to silence a demo error.
    what_happened: Added triple-slash directive disabling strictNullChecks; CI caught it.
    root_cause: Silenced compiler instead of fixing the null path.
    impact: Null-safety gap shipped to CI; required revert.
    resolution: Removed directive; fixed the null path properly.
    new_rule: Never disable strictNullChecks or any strict TypeScript flag to silence a compiler error; fix the type instead.
    target_file: skills/typescript/SKILL.md

  - id: ERR-2026-007
    date: 2026-04-28
    count: 2
    category: development
    severity: high
    context: TypeScript monorepo rename. Agent renamed in source and adjacent test only.
    what_happened: Reported rename complete; cross-package refs still used old name.
    root_cause: Local tsc scope hides cross-package references in a monorepo.
    impact: 35 min lost first occurrence; 10 min second.
    resolution: Added project-wide grep step to rename checklist.
    new_rule: After any rename, run a project-wide grep for the old name before claiming the rename is complete.
    target_file: skills/code-quality/SKILL.md

  - id: ERR-2026-012
    date: 2026-05-04
    category: deployment
    severity: high
    context: Billing service deploy with DB migration. Agent ran rollout before migration job.
    what_happened: New image expected a column that didn't exist; readiness probes failed ~90 s.
    root_cause: Assumed migrations run at pod startup; they're a separate Helm Job.
    impact: 90 s probe failures; on-call paged.
    resolution: Ran migration Job first, then re-rolled deployment.
    new_rule: Before any deployment that includes a database migration, run the migration job to completion first.
    target_file: skills/review-deployment/SKILL.md

  - id: ERR-2026-014
    date: 2026-05-13
    category: development
    severity: medium
    context: pytest fixtures returning mutable dict shared across tests.
    what_happened: First test mutated fixture; second received already-mutated object. Flaky in CI.
    root_cause: Fixture returned mutable object by reference; no fresh instance per test.
    impact: 2 h debugging cross-test pollution.
    resolution: Changed fixture to factory callable returning fresh dict per invocation.
    new_rule: Never return mutable objects from pytest fixtures; use factory fixtures that create fresh instances per invocation.
    target_file: skills/python/SKILL.md

  - id: ERR-2026-016
    date: 2026-05-13
    category: development
    severity: medium
    context: API client retry logic caught broad Exception, silently retrying a TypeError.
    what_happened: None dereference retried 3x before failing; 4 h debugging.
    root_cause: Overly broad except caught programming errors that should crash immediately.
    impact: Real error buried in retry logs.
    resolution: Narrowed catch to ConnectionError and Timeout only.
    new_rule: Always catch specific exception types rather than broad base classes in retry or error recovery logic.
    target_file: skills/code-quality/SKILL.md

  - id: ERR-2026-017
    date: 2026-05-13
    category: development
    severity: medium
    context: is_palindrome implemented before tests; empty-string edge case missed.
    what_happened: Tests validated code-as-written; empty string returned True instead of False.
    root_cause: No failing test first; no signal that empty-string was unhandled.
    impact: Bug shipped.
    resolution: Rewrote with TDD; empty-string test failed first, drove correct implementation.
    new_rule: Always write a failing test before implementing new behavior to ensure tests validate intended behavior.
    target_file: skills/tdd/SKILL.md

  - id: ERR-2026-018
    date: 2026-05-13
    category: development
    severity: medium
    context: Agent applied a fix to a reported bug without first reproducing it.
    what_happened: Bug recurred within two days under a slightly different input path.
    root_cause: No reproduction case; no way to confirm the fix addressed the actual failure mode.
    impact: Duplicate bug report; additional debugging cycle wasted.
    resolution: Wrote a minimal reproduction test, traced to root cause, fixed the invariant.
    new_rule: Before fixing a bug, reproduce it on demand and encode the reproduction as an automated test first.
    target_file: skills/debugging/SKILL.md

  - id: ERR-2026-019
    date: 2026-05-13
    category: security
    severity: high
    context: REST API with RBAC. Agent added admin endpoint without ownership check.
    what_happened: Any authenticated admin could delete any user's record by supplying an arbitrary ID.
    root_cause: Role check treated as sufficient; resource ownership never verified.
    impact: Privilege escalation; any admin could delete records belonging to other users.
    resolution: Added ownership assertion before delete; returns 403 if caller does not own the record.
    new_rule: Always verify resource ownership in addition to role-based access on mutation endpoints.
    target_file: skills/security-review/SKILL.md

  - id: ERR-2026-020
    date: 2026-05-13
    category: development
    severity: medium
    context: P