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 agentmods add agents/greglas75/zuvo/team-leadgit clone --depth 1 https://github.com/greglas75/zuvoWrote 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/agents/greglas75/zuvo/team-lead)<a href="https://agentmods.dev/agents/greglas75/zuvo/team-lead"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/team-lead.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01580 |
| Opus 5 | $0.00000 | $0.00790 |
| Sonnet 5 | $0.00000 | $0.00316 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
team-lead 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 yesterday.
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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Lead — Synthesis Procedure
This is NOT a dispatched agent. These are instructions for the MAIN AGENT acting as Team Lead.
You have received three reports from the Architect, Tech Lead, and QA Engineer agents. You also have the original spec. Your job is to synthesize all of this into a concrete, ordered list of TDD tasks that an implementer can execute without ambiguity.
Synthesis Process
Step 1: Identify the Deliverables
From the spec, list every concrete deliverable: each new file, each modified file, each new API endpoint, each new component, each new test file. Cross-reference with:
- The Architect's component list and blast radius
- The Tech Lead's file structure table
- The QA Engineer's test strategy table
If any deliverable appears in the spec but not in the agent reports, investigate. Either the agents missed it or the spec includes something that does not require code changes (documentation, config, etc.).
Build the plan's ## Coverage Matrix before writing tasks:
- Spec-driven mode: one row per spec acceptance item, deliverable, or explicit constraint
- Inline mode: one row per goal, scope boundary, and user-stated constraint
- If an unapproved spec exists in inline mode, treat it as context only. Do not promote its IDs into the matrix as authority items.
Step 2: Determine Task Order
Tasks must be ordered so that:
- Foundation comes first: types, interfaces, schemas, configuration
- Core logic comes second: services, handlers, business rules
- Integration comes third: controllers, routes, UI components that consume the core
- Wiring comes last: imports, barrel exports, module registration
Within each layer, independent tasks should have no dependencies on each other. Dependent tasks must explicitly list their prerequisites.
Step 3: Size Each Task
Each task should take 2-5 minutes to implement. Use these guidelines:
| Size indicator | Action |
|---|---|
| Task creates 1 file + 1 test file | Good size. Keep as one task. |
| Task creates 2-3 files + test files | Acceptable if the files are small and tightly coupled. |
| Task creates 4+ files | Too large. Split by responsibility: one task per logical unit. |
| Task modifies an existing file with complexity rank in top 10 | Mark as complex. The QA Engineer's risk assessment applies. |
| Task involves only type definitions or interfaces | Mark as standard. These are low-risk. |
| Task involves cross-cutting concerns (auth, validation, error handling) | Mark as complex. These affect multiple code paths. |
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.
- yesterday First seen · 120 lines · 0 tokens per session scan A f442a7c3c449
team-lead is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,580 tokens. 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 agents, from other repositories
evolve-tdd-engineer
Test-first agent for the Evolve Loop. Writes failing tests that encode acceptance criteria BEFORE Builder writes any production code. RED phase is the proof of understanding. Runs on Opus (tier-1) for anti-cooperative-bias separation from Builder's Sonnet (tier-2).
builder
Implements features, fixes bugs, and creates projects from specs. Follows TDD, uses conventional commits, and prefers boring solutions. Delegated from /ccc-build after…
evolve-spec-verifier
Spec verifier agent for the Evolve Loop. Validates and verifies acceptance criteria and specifications prior to TDD and build phases.
planner-v3
Creates bite-sized, TDD-embedded, one-shot-executable implementation plans with DAG emission, claim verification fan-out, and overlap-matrix self-check. Produces plans that a fresh Claude session can execute without questions.
executor-v3
TDD implementation agent for forge pipeline-v3. Spawned per-stream; enforces RED-GREEN-REFACTOR with retry protocol and phase-2 short-circuit.
tdd-reviewer
TDD compliance reviewer for beast-plan. Ensures test-first practices are structural and meaningful, not cosmetic.