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 commands/dgunning/edgartools/roadmapgit 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 | $0.00019 | $0.01846 |
| Opus 5 | $0.00010 | $0.00923 |
| Sonnet 5 | $0.00004 | $0.00369 |
| Haiku 4.5 | $0.00002 | $0.00185 |
Grade A, and why
roadmap 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:
- roadmap — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Roadmap Command
Use the Product Manager agent to update and maintain the living ROADMAP.md document based on GitHub issues, user feedback, velocity data, and strategic priorities.
Living Document:
docs-internal/planning/ROADMAP.mdLast Updated: Check file header Review Cycle: Weekly (Monday) and after each release
Usage Examples
# Update roadmap with current state (standard weekly review)
/roadmap
# Include detailed GitHub issues analysis
/roadmap --analyze-issues
# Focus on specific upcoming version
/roadmap --version=4.20.0
# Review and adjust priorities
/roadmap --review-priorities
# Generate strategic quarterly view
/roadmap --quarterly
Command Implementation
I'll update the living ROADMAP.md document using Product Manager agent analysis:
Step 1: Read Current Living Documents
echo "=== Reading Living Documents ==="
# Read current roadmap state
!cat docs-internal/planning/ROADMAP.md
# Read current priorities
!cat docs-internal/planning/PRIORITIES.md
# Read velocity tracking data
!cat docs-internal/planning/VELOCITY-TRACKING.md
# Get recent releases
!git log --oneline --since="1 month ago" | grep -E "(Release|release)" | head -10
Step 2: Analyze GitHub Issues & Community Feedback
echo "=== Analyzing Community Input ==="
# Get open issues by label
!gh issue list --state=open --limit=30 --json number,title,labels,createdAt,comments
# Get recent discussions
!gh api repos/{owner}/{repo}/discussions --jq '.[] | select(.category.name == "Ideas") | {number, title, comments}'
# Check for high-engagement issues
!gh issue list --state=open --json number,title,comments --jq 'sort_by(.comments) | reverse | .[0:5]'
Step 3: Product Manager Roadmap Update
I'll use the Product Manager agent to update the living roadmap:
Use the product-manager agent to update the living ROADMAP.md document:
**Context**:
- Current ROADMAP.md, PRIORITIES.md, VELOCITY-TRACKING.md (already read)
- Recent GitHub issues and community feedback (already analyzed)
- EdgarTools mission: Simple yet powerful, accurate financials, beginner-friendly, joyful UX, beautiful output
- AI-assisted velocity: 2-10x faster than traditional development
**Your Task**:
## 1. Review "Recently Completed" Section
- Verify v4.19.1 and v4.19.0 are properly documented
- Check if any older completions should be archived
- Ensure timeline and outcomes are accurate
## 2. Update "Critical Bugs (Point Releases)" Section
- Check current state: "None currently" or active critical bugs?
- If new critical bugs from GitHub, add to "Pending Point Release 4.19.X" subsection
- Follow format: Issue #XXX, severity, impact, timeline
## 3. Review Upcoming Version Sections (v4.20.0, v4.21.0, Q1 2026)
- Check if queued features from PRIORITIES.md are reflected
- Verify priority scores and estimates are current
- Add any new HIGH priority features from recent issues
- Remove or demote features that are no longer relevant
## 4. Assess Backlog Section
- Review lower priority items
- Add new MEDIUM/LOW features from recent GitHub activity
- Archive features with no user demand or superseded by better approaches
## 5. Strategic Adjustments
Based on:
- **Velocity data**: Are we on track? Adjust timelines if needed
- **User feedback**: Are we addressing highest-value requests?
- **Market positioning**: Are we strengthening core differentiators?
## 6. Update Metadata
- Update "Last Updated" date
- Set "Next Review" date (weekly Monday or after releases)
- Update velocity numbers if changed
**Output**:
Provide the specific sections of ROADMAP.md that should be updated, with exact markdown text to add/change/remove.
**Important**:
- Maintain existing structure and format
- Reference PRIORITIES.md for work queue alignment
- Reference VELOCITY-TRACKING.md for AI multipliers
- Keep user-focused language (avoid internal jargon)
- Maintain version numbering consistency
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 · 229 lines · 19 tokens per session scan A a392323cce2e
roadmap is a command published in the GitHub repository dgunning/edgartools (2,635 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 1,846 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.