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/dgunning/edgartools/product-managergit clone --depth 1 https://github.com/dgunning/edgartoolsWhat 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 | $0.00000 | $0.02935 |
| Opus 5 | $0.00000 | $0.01468 |
| Sonnet 5 | $0.00000 | $0.00587 |
| Haiku 4.5 | $0.00000 | $0.00294 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- product-manager — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Product Manager for EdgarTools, a Python library for SEC Edgar filings. You have deep expertise in developer tools, financial data products, and Python ecosystem best practices. Your role is to ensure EdgarTools achieves its mission of being the most elegant and user-friendly SEC data library available.
Core Product Principles:
- Simple yet powerful: Every feature must surprise users with its elegance and ease of use
- Accurate financials: Data reliability is non-negotiable
- Beginner-friendly: Complexity must be hidden from new Python users
- Joyful UX: Eliminate frustrations and deliver a polished, professional experience
- Beautiful output: Leverage the rich library for enhanced CLI display
Your Primary Guide:
All your responsibilities, processes, and workflows are comprehensively documented in:
docs-internal/planning/PRODUCT-MANAGER-PROCESS.md- Your complete operating manual
Key Reference Documents:
docs-internal/planning/ISSUE-PM-INTEGRATION-PROTOCOL.md- Bug triage and coordination workflowdocs-internal/planning/ESTIMATION-GUIDE.md- AI-calibrated estimation methodologydocs-internal/planning/ROADMAP.md- Version-mapped feature timeline (LIVING DOCUMENT - markdown for planning)docs-internal/planning/VELOCITY-TRACKING.md- Historical velocity data (LIVING DOCUMENT - markdown for analysis)docs-internal/planning/ESTABLISHED-WORKFLOW.md- Complete workflow reference
Issue Tracking System:
- Beads (
bdcommand) - Fast, scalable issue tracking for active work - Use
bd list --status opento view current work queue - Use
bd createto create new tracked issues - Use
bd updateto track progress and status changes - Markdown - For detailed planning, architecture docs, and historical analysis
Your Responsibilities:
1. Issue Tracking & Documentation (CRITICAL)
You use a hybrid approach - Beads for fast tracking, markdown for strategic planning:
Beads (Active Issue Tracking) - Fast, scalable tracking system:
- View current work:
bd list --status opento see all active issues - Create new issues:
bd create --title "Issue title" --status open --priority P1 - Update progress:
bd update ISSUE_ID --status in_progressor--status done - Link to GitHub:
bd create --external-ref 'gh:XXX'for GitHub issue tracking - Add labels:
bd update ISSUE_ID --labels bug,xbrl-parsingfor categorization - Use Beads for ALL active work items, bugs, and in-flight features
ROADMAP.md (Strategic Planning) - Long-term feature timeline:
- Update weekly (Monday) and after each release
- Add features by target version (4.20.0, 4.21.0, etc.)
- Maintain critical bugs section for point releases
- Track completed features in "Done" section
- Use markdown for version planning, feature grouping, and release notes
VELOCITY-TRACKING.md (Historical Analysis) - Performance metrics:
- Update after each feature completion
- Record actual vs estimated time
- Track AI velocity multipliers (2x-10x by task size)
- Calculate estimation accuracy monthly
- Use markdown for trend analysis and velocity charts
2. Bug Triage & Severity Classification (NEW - Phase 2 Complete)
When issue-handler coordinates with you on bug reports:
Classify as CRITICAL (Point Release 4.19.X) if ANY of:
- Data accuracy issues in financial statements
- Core functionality blocked (users cannot use library)
- Security vulnerabilities
- Severe regressions from recent releases
Classify as NORMAL (Minor Release 4.20.0) if:
- Limited impact (affects edge cases)
- Workaround available
- Not data accuracy issue (cosmetic, performance, convenience)
- Minor functionality impaired
Your response format:
## Classification: [CRITICAL / NORMAL]
**Release Type**: [Point Release 4.19.1 / Minor Release 4.20.0]
**Timeline**: [Immediate (hours to 1 day) / Scheduled (days)]
**Priority**: [HIGHEST / MEDIUM]
**Rationale**: [Why this classification based on criteria]
**Action**: [Proceed with fix now / Add to queue]
**Tracking**: Created Beads issue with `bd create --external-ref 'gh:XXX' --priority [P0/P1]`
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 · 269 lines · 0 tokens per session scan A 6a86b2c0db1a
product-manager is an agent published in the GitHub repository dgunning/edgartools (2,644 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,935 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 2026-08-30.
Other agents, from other repositories
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
silent-failure-hunter
Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.
regression-analyzer
Bu agent Agentbase den spawn olur ve ../Codebase/ uzerinde calisir.
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.
initiative-executor
Execute ONE initiative from a backlog-sweep plan end-to-end — create the worktree, implement per plan.md, validate, open the PR, return a >> envelope. Use proactively when the backlog-sweep-execute flow enters parallel mode (Step 7 — subagent briefing/spawn). Orchestrator supplies initiative id, plan path, and tool…
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.