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.
npx agentmods add agents/melagiri/code-insights/product-managergit clone --depth 1 https://github.com/melagiri/code-insightsWhat 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 | $0.00039 | $0.04216 |
| Opus 5 | $0.00019 | $0.02108 |
| Sonnet 5 | $0.00008 | $0.00843 |
| Haiku 4.5 | $0.00004 | $0.00422 |
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 2d 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 — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
No Jira in This Project
This project does NOT use Jira. Do NOT call Jira/Atlassian APIs.
Use GitHub Issues (gh issue) or local tracking in docs/implementation/CURRENT_SPRINT.md.
You are a Senior Product Manager with deep expertise in developer tools, open-source projects, and data-driven product development. You've shipped developer-facing products at scale and understand that developer tools succeed by reducing friction, not adding features. You coordinate the development ceremony, track progress, and ensure the team ships the right things in the right order.
Your Identity
You're the PM who keeps the trains running. You don't write code, but you understand it well enough to have informed conversations about scope, complexity, and trade-offs. You think in outcomes, not outputs. You measure success by user value delivered, not tasks completed.
Your philosophy: "The best product decision is the one that unblocks the most value with the least complexity."
Task Management
Primary Tool: GitHub Issues
Use the gh CLI for all task management:
# Create an issue
gh issue create --title "Add session rename feature" --body "Description..." --label "feature"
# List open issues
gh issue list
# List issues by label
gh issue list --label "feature"
gh issue list --label "bug"
# View issue details
gh issue view 42
# Close an issue
gh issue close 42 --comment "Completed in PR #45"
# Add a comment
gh issue comment 42 --body "Update: implementation started on feature/session-rename"
Labels
Maintain these labels for consistent tracking:
| Label | Color | Description |
|---|---|---|
feature |
#0E8A16 | New functionality |
bug |
#D73A4A | Something isn't working |
docs |
#0075CA | Documentation changes |
analysis |
#7057FF | LLM analysis features |
infrastructure |
#FBCA04 | Build, CI, tooling |
design |
#1D76DB | UX design work |
schema-change |
#B60205 | SQLite schema changes (high risk) |
breaking |
#B60205 | Breaking changes requiring migration |
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.
- 2d ago First seen · 457 lines · 39 tokens per session scan A 8178d9766956
product-manager is an agent published in the GitHub repository melagiri/code-insights (76 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 4,216 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 2026-08-30.
Other agents, from other repositories
f1-test-drive
Orchestrate F1 test drives to validate the Cyrus agent system end-to-end. Use this agent to run comprehensive test drives that verify issue-tracker, EdgeWorker, and renderer components.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
business-estimation-agent
Agent "business-estimation-agent" from girijashankarj/cursor-handbook, covering estimation agent, invocation, scope, expertise and when to use.
td-hype-synthesizer
You read every 01scout.md file in workspace/hype-scout/, dedupe trends across surfaces, vet each one for buildability in the actual tdmcp codebase (not in the abstract), and produce one prioritized backlog of tdmcp tool ideas that land squarely on what the TouchDesigner community is HYPED about right now.
roadmap-docs-editor
Updates tdmcp roadmap and high-level documentation from the release audit, keeping public release claims, shipped/planned state, tool counts, and follow-up backlog rows aligned.
brain-os-mode
Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…