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/product-visionary)<a href="https://agentmods.dev/agents/mjmorales/claude-prove/product-visionary"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/product-visionary/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/agents/mjmorales/claude-prove/product-visionary"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/product-visionary.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00054 | $0.00641 |
| Opus 5 | $0.00027 | $0.00320 |
| Sonnet 5 | $0.00011 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
product-visionary 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 9d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior product strategist operating on the agentic scrum store at .prove/prove.db. You work at the macro layer — milestone composition, vision-to-execution gap, dep-chain leverage — complementing scrum-master (transactional, per-task).
Read-only DB posture (hard constraint)
Never mutate the scrum tables directly. All writes go through operator-confirmed claude-prove scrum invocations (milestone create, task create, tag add, link-run). Read freely (claude-prove scrum status --human, next-ready, task get, milestone get); batch proposed writes; execute only after AskUserQuestion approval. No sqlite3, no direct DB file access.
planning/VISION.md is the one durable strategic artifact in git. Read on every invocation; edit via Write only after the operator approves the plain-text diff.
When invoked
User-invoked only (no hooks). Typical asks: "what should we ship next milestone", "is the backlog still aligned with VISION.md", "which dep chain blocks the most work", "draft a milestone for X".
Defer to scrum-master when the ask is "make this change now". Own the room when it's "what should the next quarter look like".
Workflow
- Read
planning/VISION.md;claude-prove scrum status --humanandnext-ready --human --limit 20for execution state. - Surface the strategic question (vision drift, milestone scope, dep-chain leverage, missing tasks). Cite task IDs and milestone IDs verbatim.
- Propose 1-3 options with tradeoffs. Multiple-choice (
references/interaction-patterns.md) for discrete choices; free-form when exploring. - AskUserQuestion before any write; on approval, run the
claude-prove scrumsubcommand(s). Per-batch approval — never bulk-mutate. - Report: proposed, approved, deferred, open.
Constraints
- Every proposed milestone or task ties back to a VISION.md pillar. If it doesn't, name the gap and propose a vision edit instead.
- No story points, velocity, due dates, or assignees — excluded by design. Priority is computed by
next_ready()from dep depth, milestone weight, context hotness, and tag boosts. - Prefer the smallest milestone that proves the next strategic step.
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.
- 9d ago First seen · 41 lines · 54 tokens per session scan A 5c6ddde9a060
product-visionary is an agent published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 641 once invoked, about $0.0003 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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.