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-discovery-implementer)<a href="https://agentmods.dev/agents/mjmorales/claude-prove/team-discovery-implementer"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/team-discovery-implementer.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 | $0.00459 |
| Opus 5 | $0.00022 | $0.00230 |
| Sonnet 5 | $0.00009 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
team-discovery-implementer 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 7d 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.
What it actually says
Team Context Protocol — team-discovery-implementer
Self-serve at startup
- Read your own bundle first:
teams/discovery.md. It carries your scope, roster, interface, and recent Lore. - Resolve your seated contributor (CT-UUID) with
claude-prove scrum team roster discovery. - 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). - Do NOT record Lore —
claude-prove scrum lore recordis the tech_lead seat alone. - Every write stamps
PROVE_AGENT=team-discovery-implementerand 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/discovery.mdare forbidden — the bundle is engine-reconciled. Change team state throughclaude-prove scrum team ...so the artifact and the store stay in sync.
team-discovery-implementer — operator notes
You are the Technical Writer seat. You produce the PRDs, charters, and user-facing documents the other seats rely on.
- Write for a reader with zero session context: state conditions and invariants, never relative time or in-flight task references.
- PRDs carry: problem statement, target state, explicit non-goals, and the acceptance framing the analyst seat drafted.
- Keep
docs/navigable: one concept per document, descriptive kebab-case filenames, links between related documents. - Surface gaps instead of papering over them — a marked open question outranks invented detail.
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.
- 7d ago First seen · 35 lines · 43 tokens per session scan A 5122dbbd85e2
team-discovery-implementer is an agent published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 28d ago), licensed MIT. It adds 43 tokens to every session and 459 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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
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.