Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gosha70/code-copilot-team --skill team-lead-efficiencygit clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gosha70/code-copilot-team/team-lead-efficiency)<a href="https://agentmods.dev/skills/gosha70/code-copilot-team/team-lead-efficiency"><img src="https://agentmods.dev/badge/skills/gosha70/code-copilot-team/team-lead-efficiency/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gosha70/code-copilot-team/team-lead-efficiency"><img src="https://agentmods.dev/badge/skills/gosha70/code-copilot-team/team-lead-efficiency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.01837 |
| Opus 5.5 | $0.00012 | $0.00735 |
| Sonnet 5.5 | $0.00006 | $0.00367 |
| Haiku 4.5 | $0.00003 | $0.00184 |
Grade A, and why
team-lead-efficiency scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Lead Efficiency
Rules for the lead agent when coordinating sub-agents to minimize waste and maximize throughput.
Task Scoping
Right-Size the Work
- 2-3 teammates is the sweet spot for most features. More than 3 increases coordination overhead without proportional speedup.
- Each teammate task should take 5-30 minutes. If a task takes over an hour, it's too large — break it up.
- If a task would touch fewer than 3 files, the lead should do it directly instead of delegating.
Non-Overlapping Ownership
Every file must have exactly ONE owner for a given phase:
Bad:
Agent A: Implement product service (touches product model, router, UI)
Agent B: Implement order service (also touches product model for inventory)
Good:
Agent A: Implement product service (owns product.service, product.router)
Agent B: Implement order service (owns order.service, order.router)
Lead: Handles shared code (product model changes for inventory) after both complete
The lead handles shared/cross-cutting code after teammates return — not in parallel.
Clear Boundaries in the Delegation Prompt
Every delegation must include:
- Exact files to create or modify (not "implement the feature").
- Read-only context files — schema, types, design docs the agent should reference but NOT modify.
- Interface contracts — what inputs/outputs must match.
- What NOT to do — explicit exclusions prevent scope creep.
Polling Discipline
Do Not Busy-Wait on Teammates
After launching sub-agents, the lead should:
- Launch all independent agents at once (parallel, not sequential).
- Work on non-overlapping tasks while waiting (documentation, tests, review plans).
- Check status periodically — not continuously. Polling once per minute is sufficient.
- Never re-do teammate work. If a teammate is slow, wait or stop them — don't duplicate their output.
When to Stop a Teammate
Stop a running teammate if:
- Its task is no longer needed (requirements changed).
- The lead has already completed the work (this means the task was mis-delegated).
- The agent has been running over 2x the expected duration with no progress.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 143 lines · 29 tokens per session scan A dca8cdd09bdc
team-lead-efficiency is a skill published in the GitHub repository gosha70/code-copilot-team (7 stars, last pushed 17d ago), licensed MIT. It adds 29 tokens to every session and 1,837 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
agent-deck
Helper scripts live in this skill's scripts/ folder. Resolve them from the base directory shown when the skill loaded, not from the user's project.
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
deck-repro
Reproduce agent-deck bugs from an issue, transcript excerpt, or description in an isolated environment, and prove fixes with the same reproduction and a regression test. Use for a concrete agent-deck issue or candidate, verifying a fix, preparing a contributor bug-fix PR, or when deck-retro passes a candidate. Broad…