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-syncnpx skills add friedbotstudio/baseline --skill roadmap-syncgit 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 | $0.00171 | $0.01628 |
| Opus 5 | $0.00086 | $0.00814 |
| Sonnet 5 | $0.00034 | $0.00326 |
| Haiku 4.5 | $0.00017 | $0.00163 |
Grade A, and why
roadmap-sync 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
roadmap-sync — Phase 10.6
Runs after /archive (10.5) and before /memory-sync (10.7) on every committing track. Keeps the project's execution roadmap (project.json → roadmap.path) in sync with landed work, so the roadmap tracker never drifts from what actually shipped. The roadmap is a plan, never a gate.
The phase does one of two things depending on the track. On a track that lands code it flips rows the work completed. On the epic track — which lands discovery, not code — there is no row to flip yet, so it appends the epic's own section. Both directions are additive-only: nothing already on the roadmap is renumbered, reordered, or removed.
Prereq
archive is in workflow.json → completed OR in exceptions. If neither, stop and direct the user to run /archive first (or /harness to resume in order).
Steps
- Resolve inputs. Read
project.json → roadmap.pathand resolve it against the repo root withresolveRoadmapPath(empty/absent/absolute/repo-escaping →null). Readworkflow.json → roadmap_tasks[](absent →[]) —/triagepopulates this with validatedE<epic>-<taskId>tokens when the request isspec-derivedagainst a roadmap item. If the path resolves tonull, the phase is a clean no-op — skip to Step 3. An emptyroadmap_tasksdoes not skip the sync: the heal pass in Step 2 is why the phase runs on every committing workflow, and an epic whose rows this workflow never touched is exactly the one whose heading nothing else repairs. - Sync. Call
syncRoadmap({ roadmapPath, roadmapTasks })fromsync.mjs. It flips eachE<num>-<taskId>token's task line ⬜→✅, recomputes each affected epic heading ⬜→🟡→✅, then heals — recomputes every remaining epic heading against its own task body and reports the ones that moved underhealed[]. It writes the roadmap file only if something changed. It never throws — on any error it returns a no-op result and writes nothing. - Record the phase. Append
"roadmap-sync"toworkflow.json → completedand refreshupdated_at. - Report. Emit the
SyncReportJSON ({flipped, promoted, healed, skipped, noop, anomalies}) and append a one-lineroadmap-syncentry to.claude/state/harness/<slug>.log(flipped=[..] promoted=[..] healed=[..] noop=<bool>). Surface anyanomalies[]to the user as non-blocking notes, and name anyhealed[]epic explicitly — a heading that moved for a reason unrelated to this workflow is the one change in the diff the author cannot otherwise account for.
What ships with it
5 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 · 51 lines · 0 tokens per session scan A 7dd06d196d27
roadmap-sync is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 171 tokens to every session and 1,628 once invoked, about $0.0009 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.