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/roadmapnpx skills add friedbotstudio/baseline --skill roadmapgit 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 | $0.00117 | $0.00941 |
| Opus 5 | $0.00059 | $0.00470 |
| Sonnet 5 | $0.00023 | $0.00188 |
| Haiku 4.5 | $0.00012 | $0.00094 |
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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
roadmap — what is left, and what is next
A read-only reader over the execution plan named by project.json → roadmap.path, in the family of standup and audit-baseline: it reads state and reports, it never mutates. It is not a workflow phase — it does not enter the Track Guard ordering and never blocks a commit.
standup answers six questions and the roadmap is one of them, so it bounds the roadmap section and drops to tallies on a large plan. This command answers only that one question, so it never collapses open rows at any plan size. What collapses instead is the finished work — that is the bulk, and it carries no pickup.
The verbs
node .claude/skills/roadmap/cli.mjs list [--all] [--epic N] [--json] [--root <dir>]
node .claude/skills/roadmap/cli.mjs tasks [--epic N] [--status done|in-progress|planned] [--json]
node .claude/skills/roadmap/cli.mjs epics [--json]
node .claude/skills/roadmap/cli.mjs next [--json]
| Verb | Answers |
|---|---|
list |
The whole plan as a reader sees it — header, rollup, open rows nested under their epic, and the next pickup. |
tasks |
Individual rows, filtered by --epic and/or --status. One line per row. |
epics |
One line per epic with its status and its done / in-progress / planned tally. |
next |
The first planned row in file order, plus the epic it belongs to. |
Every verb takes --json and prints the raw projection instead of the rendering. A missing plan file exits 2 with the path it looked for; a malformed filter exits 1 with the usage error.
What list prints
Roadmap — docs/roadmap-execution-plan.md
13 epics · 78 rows · 66 done, 0 in progress, 12 planned
✅ Epics 1-7, 10, 12 (53 rows, all done)
Epic 8 ⬜ Codebugger explanation trace (0/3 done)
⬜ A Runtime-witness rule and the mcp-debugger declaration
⬜ B The /codebugger session and the explanation trace
Next planned: Epic 8 A Runtime-witness rule and the mcp-debugger declaration
- The rollup folds every wholly-done epic into one line, compressing consecutive numbers into ranges. A lone finished epic reads
Epic 4, never4-4. - Open rows are planned and in-progress rows. Every one of them renders, however many there are.
--allexpands the rollup: each epic gets its own header and its done rows render too.--epic Nscopes the view to one epic. Naming an epic is itself a request to see it, so a scoped view never collapses.
What ships with it
3 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 · 57 lines · 117 tokens per session scan A cc12ea981376
roadmap is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 117 tokens to every session and 941 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 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.