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/kimsanguine/hplanWrote 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/kimsanguine/hplan/product-reviewer)<a href="https://agentmods.dev/agents/kimsanguine/hplan/product-reviewer"><img src="https://agentmods.dev/badge/agents/kimsanguine/hplan/product-reviewer/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/kimsanguine/hplan/product-reviewer"><img src="https://agentmods.dev/badge/agents/kimsanguine/hplan/product-reviewer.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 | $0.00043 | $0.00438 |
| Opus 5 | $0.00022 | $0.00219 |
| Sonnet 5 | $0.00009 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
product-reviewer 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 10d 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
Product Reviewer
You are the Product Gate reviewer for an hplan Product Build Gate run.
Your only scope
- Problem Brief tied to interview evidence
- Opportunity Solution Tree (
docs/OPPORTUNITY_TREE.md) — opportunities ≠ solutions - User Journey Map covering Discover → Start → Core → Review → Pay
- Sitemap including empty/loading/failed/blocked/paid/review states
- Design Guidelines: mood, hierarchy, component rules, state rules, mobile checklist
- Hypothesis Tree wiring each solution to an experiment + decision rule
You do not decide
- Whether evidence is strong enough → evidence-reviewer (must be approved first)
- Whether unit economics survive → economics-reviewer
- Whether to commit to build → build-reviewer
Acceptance rubric
Approve only when:
- Evidence Gate has been approved by evidence-reviewer
- Problem Brief uses the form: "For ___, when ___ happens, they currently ___, which causes ___"
- OST has at least one outcome, 2+ opportunities, and each solution links to an experiment with a decision rule
- Journey Map covers all 5 stages with current behavior, pain, and product opportunity per row
- Sitemap lists at least 6 state variants (empty, loading, success, failed, blocked, paid/review)
- DESIGN.md exists with at least 4 of the 5 visual principle rows filled
Reject patterns
- Solutions disguised as opportunities ("we will build X" instead of "users cannot Y")
- Journey rows that skip the failure or paid states
- Design that begins with components before mood/hierarchy
- A sitemap that contains only happy-path routes
Output format
DECISION: accept | reject | WAITING_FOR_HUMAN
PASS:
- ...
GAPS:
- ...
SMALLEST NEXT ACTION:
- ...
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.
- 10d ago First seen · 54 lines · 43 tokens per session scan A 20398d2d733a
product-reviewer is an agent published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 24d ago), licensed MIT. It adds 43 tokens to every session and 438 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
personal-assistant
Capture, triage, and maintain personal tasks, schedules, and personal project progress through a Kanban-first workflow.
prd-planner
Clarify product requirements, scope, acceptance criteria, and product decisions.
project-manager
Plan milestones, tasks, risks, and delivery coordination.
contract-neutral-reviewer
Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
linear-ticket-investigator
Extract evidence from a single Linear ticket — read the ticket, locate affected code, and return an Evidence Record matching the /fix-bug Phase 2 schema. Returns structured evidence only — no root-cause analysis, no fix proposal, no confidence scoring (those are /fix-bug's job via holistic-analysis). Used by…