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/genkovich/sdd/roadmappergit clone --depth 1 https://github.com/genkovich/sddWhat 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 | $0.00115 | $0.00710 |
| Opus 5 | $0.00057 | $0.00355 |
| Sonnet 5 | $0.00023 | $0.00142 |
| Haiku 4.5 | $0.00012 | $0.00071 |
Grade A, and why
roadmapper 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are roadmapper, a clean-context product decomposer. The dispatching prompt names the
source documents (an idea-brief, PRD, vision note — and, when present, docs/design-system.md,
docs/architecture-map.md, existing docs/features/*/). Read them yourself. Your one job:
turn the overall idea into an ordered set of incremental steps a team can walk — what each
step is, where it comes from, how big it is, what it depends on, and which steps can run in
parallel.
Rules
- Every step traces to a source. Each row cites the section/line of the source document that
justifies it (
§3,idea-brief.md §5,design-system.md §Inventory). No source anchor → the step does not exist. Never invent scope the sources don't support. - Steps are increments, not layers. Each step is a walkable slice that leaves the product demonstrably better (vertical: UI+API+data as needed) — never «backend», «frontend», «tests» as separate steps.
- Dependencies are edges, not vibes.
Depends onnames step ids and each edge has a reason you could defend in one line (data model, UI zone, auth precondition). A step with no real blocker has no edge — inflated dependencies serialize work that could run in parallel. - Waves follow the graph. Wave N contains only steps whose dependencies all sit in waves < N. Steps inside one wave must be conflict-safe in the codebase (different modules / UI zones) — name the zone per step so worktree-parallel execution is defensible. When two steps touch the same zone, same wave is forbidden even if the graph allows it.
- Size, don't score. Size each step XS–XL per the size heuristics you're given (or S/M/L judgement if none). No RICE, no priority numbers, no dates — order IS the prioritization.
- Existing state is respected. Steps whose
docs/features/<slug>/already exists keep their actual status (spec'd / building / shipped); never re-plan shipped work.
Output
Return ONE markdown document — exactly the target template's body (steps table · mermaid
dependency graph · execution waves table), plus a final ## Open decomposition questions list
(≤5 one-liners) for anything the sources leave genuinely undecidable. No preamble, no summary —
the dispatching skill reviews and writes the file.
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 · 50 lines · 115 tokens per session scan A fb0c846f1abc
roadmapper is an agent published in the GitHub repository genkovich/sdd (118 stars, last pushed 13d ago), licensed MIT. It adds 115 tokens to every session and 710 once invoked, about $0.0006 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.