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 skills/friedbotstudio/baseline/roadmap-plannernpx skills add friedbotstudio/baseline --skill roadmap-plannergit clone --depth 1 https://github.com/friedbotstudio/baselineWhat 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 | $0.00294 | $0.03711 |
| Opus 5 | $0.00147 | $0.01855 |
| Sonnet 5 | $0.00059 | $0.00742 |
| Haiku 4.5 | $0.00029 | $0.00371 |
Grade A, and why
roadmap-planner 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
roadmap-planner
Prove an execution roadmap's task order is correct by re-deriving it from the source of truth (the vision + spec), then diffing the derivation against the existing plan.
The core insight: a roadmap is a schedule over a dependency graph. Most planning errors are not "wrong task" — they are producer-after-consumer: a task that produces something (a contract, a schema, an SDK, a service) is scheduled after a task that consumes it. Reading the roadmap top-to- bottom never catches this; only building the actual dependency graph does. So we derive the tasks from use-cases, wire the graph explicitly, and let a deterministic pass find every ordering violation.
You produce two artifacts, never a silent overwrite:
- a freshly-derived, dependency-ordered roadmap (a proposal), and
- a delta report vs the existing roadmap — ordering violations, missing/extra tasks, circular dependencies found + how they were broken, and compaction candidates.
The human reviews the delta and decides what to adopt. The existing roadmap is often hand-crafted with context the spec doesn't capture; the derivation's job is to challenge it, not replace it.
Inputs (parameterize per project)
- Corpus — the vision/spec/requirements docs to derive from. Point it at wherever the project keeps
its source of truth (a
docs/spec/**tree, a product-requirements doc, a genesis/seed file, ADRs). Actors + use-cases usually live in the requirements/product docs; modules/engines/services in the architecture/design docs. If the project has no written spec, derive from the README + issue tracker and flag the thin provenance as a finding. - Existing roadmap — the plan to validate. Default:
project.json → roadmap.path(this baseline's default isdocs/roadmap-execution-plan.md). - Buckets — the delivery lanes, project-defined. Set them in the
tasks.jsontop-levelbucketsarray; they only rank ties in ordering. A single-lane project can use one bucket (e.g.app); a platform/product split might useplatform,product,web,app. There is no fixed lane set.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 202 lines · 294 tokens per session scan A fe6265eb0479
roadmap-planner is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 294 tokens to every session and 3,711 once invoked, about $0.0015 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 skills, from other repositories
dev-standards
Enforces development workflows, quality gates, coding standards, and release processes for the deterministic-agent-control-protocol project. Use when implementing features, fixing bugs, refactoring architecture, adding integrations, updating policies, writing tests, updating documentation, or preparing releases.
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
国际化完整性检查。检查翻译 key 是否缺失、硬编码文本、locale 文件一致性。.
vue-best-practices
Vue 2/3 代码规范检查。包括组件命名、Props 校验、Composition API 规范等。.
python-review
Python 遗留代码审查：bare except、SQL 注入、反序列化、密钥、调试输出.
rust-review
Rust 服务审查：panic、SQL 注入、密钥、错误吞没、遗留标记.