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/Dokkabei97/forged-claude-codeWrote 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/commands/dokkabei97/forged-claude-code/roadmap-builder)<a href="https://agentmods.dev/commands/dokkabei97/forged-claude-code/roadmap-builder"><img src="https://agentmods.dev/badge/commands/dokkabei97/forged-claude-code/roadmap-builder/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/commands/dokkabei97/forged-claude-code/roadmap-builder"><img src="https://agentmods.dev/badge/commands/dokkabei97/forged-claude-code/roadmap-builder.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 | $0.00029 | $0.00954 |
| Opus 5.5 | $0.00012 | $0.00382 |
| Sonnet 5.5 | $0.00006 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
roadmap-builder 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/roadmap-builder - Product Roadmap Generator
Triggers
- Quarterly planning sessions
- Investor/board updates requiring roadmap
- Aligning team on what's coming next
Usage
/roadmap-builder
/roadmap-builder --format now-next-later
/roadmap-builder --format timeline
/roadmap-builder --quarter Q2-2026
Behavioral Flow
Phase 1: Input Collection
Gather roadmap inputs:
1. Strategic goals (from OKRs or company objectives)
2. Prioritized feature list (from feature-prioritizer)
3. Team capacity (people × weeks available)
4. Dependencies and constraints
5. Audience (internal team / investors / customers)
Phase 2: Framework Selection
Now-Next-Later (recommended for startups):
## Product Roadmap
### 🟢 NOW (This Month/Sprint)
Committed work, high confidence.
- [Feature] — [Owner] — [Status]
### 🟡 NEXT (Next 1-3 Months)
Planned work, medium confidence.
- [Feature] — [Why now]
### 🔴 LATER (3-6 Months)
Exploratory, low confidence. Subject to change.
- [Feature] — [Depends on]
### 🗑️ NOT DOING
Explicitly decided against.
- [Feature] — [Why not]
Timeline (Gantt-style, for investors/board):
gantt
title Product Roadmap Q2 2026
dateFormat YYYY-MM-DD
section Core Product
Feature A :a1, 2026-04-01, 30d
Feature B :a2, after a1, 20d
section Growth
Feature C :b1, 2026-04-15, 25d
Feature D :b2, 2026-05-15, 30d
section Infrastructure
Feature E :c1, 2026-04-01, 45d
Phase 3: Generate Roadmap
# Product Roadmap — [Period]
**Last Updated**: YYYY-MM-DD
**Owner**: [CPO/PM Name]
**Strategy**: [1-sentence strategic context]
---
## Strategic Goals This Quarter
1. [Goal 1 — linked to OKR]
2. [Goal 2 — linked to OKR]
## Roadmap
### 🟢 NOW — [Month]
| Feature | Goal Link | Owner | Status | ETA |
|---------|-----------|-------|--------|-----|
| [Feature] | Goal 1 | @name | In Progress | Week N |
### 🟡 NEXT — [Month+1 to Month+3]
| Feature | Goal Link | Why Next | Confidence |
|---------|-----------|----------|------------|
| [Feature] | Goal 2 | [Rationale] | Medium |
### 🔴 LATER — [Month+3 to Month+6]
| Feature | Depends On | Open Questions |
|---------|-----------|---------------|
| [Feature] | [Dependency] | [What we need to learn first] |
---
## Key Dependencies
- [Feature A] blocks [Feature B]
- [External: API from partner] blocks [Feature C]
## Risks
| Risk | Impact | Mitigation |
|------|--------|------------|
| [Risk] | [Impact] | [Plan] |
## Change Log
| Date | Change | Reason |
|------|--------|--------|
| YYYY-MM-DD | Moved X from Now to Next | [Reason] |
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 · 141 lines · 29 tokens per session scan A 38155afacc8c
roadmap-builder is a command published in the GitHub repository Dokkabei97/forged-claude-code (2 stars, last pushed 8mo ago), licensed MIT. It adds 29 tokens to every session and 954 once invoked, about $0.0001 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 commands, from other repositories
status
Display project status, active tracks, and next actions.
amend-plan
Plan Amend - Discuss and apply amendments to a plan.json implementation plan.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
triage
Process the user-feedback queue — triage new reports, keep the status mirror honest, and (at release time only) send the shipped emails.
audit
Audit closed tickets for regressions against today's code (unchanged, evolved, implemented wrong, not implemented), plus duplicate and groupable open ones.