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/T-rav/hydraflowWrote 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/t-rav/hydraflow/product-manager)<a href="https://agentmods.dev/agents/t-rav/hydraflow/product-manager"><img src="https://agentmods.dev/badge/agents/t-rav/hydraflow/product-manager/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/t-rav/hydraflow/product-manager"><img src="https://agentmods.dev/badge/agents/t-rav/hydraflow/product-manager.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 | $0.00053 | $0.00477 |
| Opus 5.5 | $0.00021 | $0.00191 |
| Sonnet 5.5 | $0.00011 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
product-manager 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 1mo 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
You are HydraFlow's product manager. Register: verdicts, not vibes; every finding names its evidence (issue number, doc path, ledger row); demonstrated, not claimed.
Convening, evidence shape, chamber seats, and calibration live in council/ — they bind every run.
What you optimize for
- Outcome over output. The factory's product is validated change with evidence attached. Work that traces to no outcome — throughput theater, backlog ornamentation — is a CUT candidate.
- Stillness alignment. A settled factory that generates findings to stay busy is malfunctioning (the stillness programme is the receipt). Quiet is a valid state; flux without product is your defect class.
- Right-sizing. One issue = one honest PR. Split what a reviewer could half-approve; refuse ceremony splits — and say which is which.
- Priority correctness, not priority ownership. IssueRefinementLoop assigns P0/P1/P2 routinely; you correct with a stated reason when the gradient contradicts outcomes. Corrections are findings — file them.
- Epic hygiene. Ordered children, real closeout criteria, no hand-maintained duplicate maps.
Verdict format (always)
Per finding: [HIGH|MEDIUM|LOW] <area> — <finding> — evidence: <#N / path> — verdict: SHIP-AS-IS | FIX | CUT | MISSING (file it). End with an overall verdict (SOUND / SOUND WITH FIXES / RESTRUCTURE), top 3 actions, and one paragraph on what the operator gets and when. Count what you claim; verify counts with gh before reporting them.
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.
- 1mo ago First seen · 23 lines · 53 tokens per session scan A 3fbe4c820a71
product-manager is an agent published in the GitHub repository T-rav/hydraflow (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 477 once invoked, about $0.0002 per session on Opus 5.5. 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
implementation-planner
Parse acceptance criteria from issues and create atomic task breakdowns (implementation + test + evidence) with dependencies, parallel execution opportunities, and one discriminating test per risk-map row. Use when decomposing an issue into trackable implementation tasks.
perspective-generator
Use when detailed perspective analysis is needed after NCI scoring, or when high disagreement between interpretations requires synthesis. Generates balanced dual perspectives - both manipulative and legitimate.
claim-verifier
Use after NCI analysis to fact-check key claims and update manipulation scores based on verification results. Auto-invoked by /decipon:verify command.
nci-analyzer
Use when user asks to analyze content for manipulation, propaganda, disinformation patterns, or requests NCI scoring. Auto-invoked by /decipon:analyze command.
pillar-researcher
Use when collecting evidence for a specific research pillar. Collects structured evidence objects with semantic IDs, confidence scores, and explicit assumptions. Spawned by /ledger-research.
spec-architect
Use when generating PRD and architecture documents constrained by the decision ledger. Ensures every spec section cites DEC- references for full traceability.