coordinator-mode — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited coordinator-mode (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use coordinator patterns when:
Don't use coordinator patterns when:
Most coordinated tasks follow four phases:
| Phase | Who | Purpose |
|---|---|---|
| Research | Workers (parallel) | Investigate codebase, find files, understand problem |
| Synthesis | You (coordinator) | Read findings, understand the problem, craft implementation specs |
| Implementation | Workers | Make targeted changes per spec, commit |
| Verification | Workers | Test changes work, try to break them |
The synthesis phase is the coordinator's most important job. When workers report research findings, you must understand them before directing follow-up work. Read the findings. Identify the approach. Then write a prompt that proves you understood by including specific file paths, line numbers, and exactly what to change.
Never write "based on your findings" or "based on the research." These phrases delegate understanding to the worker instead of doing it yourself.
Workers cannot see your conversation. Every prompt must be self-contained:
Good — synthesized spec: "Fix the null pointer in src/auth/validate.ts:42. The user field is undefined when sessions expire but the token is still cached. Add a null check before user.id access. Commit and report the hash."
Bad — lazy delegation: "Based on your findings, fix the auth bug." "The worker found an issue. Please fix it."
Include a brief purpose so workers calibrate depth:
| Situation | Action | Why |
|---|---|---|
| Research explored exactly the files that need editing | Continue existing worker | Worker has files in context |
| Research was broad, implementation is narrow | Spawn fresh worker | Avoid context noise |
| Correcting a failure | Continue existing worker | Worker has error context |
| Verifying code a different worker wrote | Spawn fresh worker | Fresh eyes, no implementation bias |
| Wrong approach entirely | Spawn fresh worker | Clean slate avoids anchoring |
Parallelism is the primary advantage. Launch independent workers concurrently:
For durable cross-worker knowledge, use a shared scratchpad file:
When running multiple Claude Code terminals (Boris Mode):
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.