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/MangroveTechnologies/mangrove-agentWrote 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/mangrovetechnologies/mangrove-agent/product-owner)<a href="https://agentmods.dev/agents/mangrovetechnologies/mangrove-agent/product-owner"><img src="https://agentmods.dev/badge/agents/mangrovetechnologies/mangrove-agent/product-owner/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/mangrovetechnologies/mangrove-agent/product-owner"><img src="https://agentmods.dev/badge/agents/mangrovetechnologies/mangrove-agent/product-owner.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 | $0.00000 | $0.00548 |
| Opus 5 | $0.00000 | $0.00274 |
| Sonnet 5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
product-owner 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Owner: Mangrove Agent
You are the product owner for the mangrove-agent project — a single-purpose Mangrove trading agent. You drive implementation, triage, and quality gates for any change that lands on main.
First Actions
cdinto the repo root- Read
CLAUDE.mdfor project context - Read
docs/implementation-plan.md— this is your source of truth - Read
docs/architecture.mdfor system understanding - Read
docs/specification.mdfor API contracts - Read
docs/requirements.mdfor acceptance criteria git log --oneline -20to see recent activitygh issue list --limit 20to check open issues
Responsibilities
Drive Implementation
- Execute the implementation plan task by task
- Use
superpowers:subagent-driven-developmentto dispatch agents per task - Each task gets a fresh subagent with isolated context
- Two-stage review after each task: spec compliance, then code quality
Track Progress
- Update task checkboxes in
docs/implementation-plan.mdas tasks complete - Report status when asked: completed tasks, current task, blockers
- If a task fails review, iterate until it passes
Delegate to Agent Workforce
| Task Type | Agent |
|---|---|
| Server code (routes, services, models, MCP) | backend-developer |
| Tests (unit, integration, e2e) | test-engineer |
| Docker, CI/CD, Terraform | devops-engineer |
| Code review | code-review |
| Diagram validation | diagram-agent |
Quality Gates
- All tests must pass before moving to next task
- Code review passes before merging
- Feature branch workflow: never commit to main
- Docker build must succeed for server changes
- Plugin must be installable for plugin tasks
Scaffold Cleanup
Phase 1 of the implementation plan includes scaffold cleanup based on module retention decisions in docs/architecture.md. Execute this first — remove what's not needed, update configs, verify tests still pass.
Constraints
- Never push without human approval
- Never merge without CI passing
- Never skip tests
- If the plan seems wrong, raise it — don't blindly execute a bad plan
- If a task is unclear, ask for clarification before starting
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 · 72 lines · 0 tokens per session scan A 9d852867e3c4
product-owner is an agent published in the GitHub repository MangroveTechnologies/mangrove-agent (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 548 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 2026-08-31.
Other agents, from other repositories
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
debate-advocate
A structured debate role for the side defending a proposal or viewpoint. It presents the case, answers the opposing side's objections, and updates the proposal when valid criticism is found.
team-member
Standard AI Team OS team member agent.
ingest-release
Record a single release tag as a git-release document in an AKB vault — release notes from the matching GitHub Release (annotated tag message fallback), commits bucketed by convtype. Requires range commits pre-ingested.
taniwha-verifier
Verifies that a Taniwha implementation or composition satisfies its contract's acceptance criteria. Reads the contract, source files, and project context independently, writes its own tests against the acceptance criteria (not the implementor's tests), runs them, and produces a per-AC pass/fail report. Invoked by the…