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/bvdr/claude-plugins/roadmapgit clone --depth 1 https://github.com/bvdr/claude-pluginsWhat 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 | $0.00050 | $0.05193 |
| Opus 5 | $0.00025 | $0.02596 |
| Sonnet 5 | $0.00010 | $0.01039 |
| Haiku 4.5 | $0.00005 | $0.00519 |
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 yesterday.
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 — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap Orchestrator
You are the orchestrator for the Roadmap system. You run autonomously and handle all subcommands. Read this entire file before taking any action.
Step 0: Parse Arguments
Read the skill args string and determine the subcommand and flags.
Subcommand detection (first non-flag token):
| Args | Subcommand |
|---|---|
| (empty or no non-flag tokens) | run |
help |
help |
accept <id> [<id>...] |
accept |
dismiss <id> [--reason "..."] |
dismiss |
status |
status |
create-issues |
create-issues |
create-issue <id> |
create-issue |
Flag detection (can appear alongside run):
--refresh→ setFORCE_REFRESH = true--skip-discovery→ setSKIP_DISCOVERY = true--no-open→ setNO_OPEN = true
Once you know the subcommand, jump to that section below.
Subcommand: help
Print this exact text and stop — do not run any other phase:
ROADMAP - AI-powered strategic feature roadmap generation
USAGE:
/roadmap Generate full roadmap
/roadmap --refresh Force re-run deep analysis
/roadmap --skip-discovery Re-run features only (reuse discovery.json)
/roadmap --no-open Don't auto-open HTML report
/roadmap help Show this help
REVIEW:
/roadmap accept <id> [<id>...] Mark features as accepted
/roadmap dismiss <id> [--reason ""] Mark feature as dismissed
/roadmap status Show review summary
GITHUB:
/roadmap create-issues Create GH issues for all accepted
/roadmap create-issue <id> Create GH issue for specific feature
ANALYSIS:
- Analyzes 500 commits + all merged PRs (last year)
- Reviews open issues, milestones, and active PRs
- Performs web-based competitive research
- Consumes ideation results if available (.claude/ideation/)
- MoSCoW prioritization (must/should/could/won't)
OUTPUT:
.claude/roadmap/report.html Interactive HTML report
.claude/roadmap/roadmap.json Machine-readable results
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.
- yesterday First seen · 569 lines · 50 tokens per session scan A ee5aba4d0fc4
roadmap is a command published in the GitHub repository bvdr/claude-plugins (3 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 5,193 once invoked, about $0.0003 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 2026-08-31.
Other commands, from other repositories
dead-code-scan
Scan for dead code, unused imports, duplicates, and zombie code across the project.
dead-code-clean
Actively find and remove dead code, unused imports, duplicates, and zombie code.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.
swift-critique
Critique SwiftUI code for patterns, design, clean code, accessibility, and performance.
dotnet-harden
Scan and harden .NET backend code against high-impact anti-patterns such as sync-over-async, lifetime bugs, fat endpoints, and fragile SignalR state.
dotnet-teach
One-time setup that scans a .NET backend project, learns its conventions and architecture, and writes them to CLAUDE.md for future sessions.