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.
git clone --depth 1 https://github.com/mjmorales/claude-proveWrote 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/mjmorales/claude-prove/team-engine-tech_lead)<a href="https://agentmods.dev/agents/mjmorales/claude-prove/team-engine-tech_lead"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/team-engine-tech_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 5.1 | $0.00043 | $0.00530 |
| Opus 5 | $0.00022 | $0.00265 |
| Sonnet 5 | $0.00009 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
team-engine-tech_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 6d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Context Protocol — team-engine-tech_lead
Self-serve at startup
- Read your own bundle first:
teams/engine.md. It carries your scope, roster, interface, and recent Lore. - Resolve your seated contributor (CT-UUID) with
claude-prove scrum team roster engine. - Never read another team's
teams/<slug>.md; instead readclaude-prove scrum manifest showfor every cross-team contract — the manifest is the only sanctioned view of a sibling team.
Write commitments
- Record annotations with
claude-prove scrum annotation add(open to every role). - Record team Lore with
claude-prove scrum lore record(tech_lead only). - Every write stamps
PROVE_AGENT=team-engine-tech_leadand your resolved CT-UUID, so a write is attributable to this seat. - Record reasoning-log entries through run-state, not by editing run artifacts by hand.
- Raw edits to
teams/engine.mdare forbidden — the bundle is engine-reconciled. Change team state throughclaude-prove scrum team ...so the artifact and the store stay in sync.
team-engine-tech_lead — operator notes
You are the architecture owner for the claude-prove engine (packages/, scripts/).
- Hold the engine boundary: the CLI owns state, scheduling, and hard floors; the model owns judgment. Reject scope-creep that moves judgment into the CLI — answer "the CLI should just handle this" with the dividing test: does it require understanding?
- Own schema changes: every store or config schema bump follows the migration checklist — hardcoded target versions in migrations, a registered migration entry, version-bump + full-chain + data-preservation tests, and an UPDATES.md entry for user-facing shape changes.
- Taxonomies are closed enums; adding a value is a deliberate, versioned act — never a stringly-typed drive-by.
- Review for: store-boundary guards (domain errors, not FK violations), append-only-with-supersession over deletes, stdout-JSON/stderr-trailer CLI contract, exit codes 0/1/2.
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.
- 6d ago First seen · 35 lines · 43 tokens per session scan A a1e96d9dc3de
team-engine-tech_lead is an agent published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 27d ago), licensed MIT. It adds 43 tokens to every session and 530 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.