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/sprint-plannernpx skills add friedbotstudio/baseline --skill sprint-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 | $0.00134 | $0.01041 |
| Opus 5 | $0.00067 | $0.00521 |
| Sonnet 5 | $0.00027 | $0.00208 |
| Haiku 4.5 | $0.00013 | $0.00104 |
Grade A, and why
sprint-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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sprint-planner — select the next ready sprint from the roadmap
sprint-plan decomposes a fresh vision into features. sprint-planner selects from an
already-decomposed roadmap — it does not invent features, it picks the ready, cohesive subset of
roadmap tasks and proposes them as a sprint. Same manifest schema, same sprint-oracle completeness
gate; different input (existing roadmap graph) and different verb (select, not decompose).
This is standup's active sibling: standup recaps "where are we + next single pickup"; sprint-planner
proposes "the next coherent sprint (3–4 dependency-ready tickets)" to feed the power batch-sprint track.
Step 1 — gather (reuse standup's readers)
node .claude/skills/standup/gather.mjs --root .
Use the public gatherSync({rootDir}) recap: roadmap (epics + per-task emoji status) and backlog.
Do not reach into standup's module-private readers.
Step 2 — build the task graph + status
Assemble a tasks.json (roadmap-planner's shape: {tasks:[{id, epic, bucket, category, title, deps[], order?}]}) from the roadmap in main context — the same model step roadmap-planner documents. Roadmap
dependencies are usually prose in the roadmap text; read them from the roadmap and the derived artifact
under docs/roadmap/derived-*.md when present. (A project that records structured deps: in its tracker
can feed them directly instead of re-deriving from prose.)
Order + cycle-check with the existing engine (CLI subprocess; it has no exports):
node .claude/skills/roadmap-planner/scripts/graph.mjs order <tasks.json>
node .claude/skills/roadmap-planner/scripts/graph.mjs analyze <tasks.json>
Step 3 — compute readiness + select (helper)
Readiness is computed in-planner from the roadmap's machine-readable status (a task is ready iff every
dep is done), NOT pushed into graph.mjs:
node .claude/skills/sprint-planner/planner.mjs select <input.json> [--capacity N] --json # wraps planner.mjs -> selectSprint
What ships with it
2 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 · 75 lines · 134 tokens per session scan A 2127371ded11
sprint-planner is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 134 tokens to every session and 1,041 once invoked, about $0.0007 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.
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。.
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。.
rust-review
Rust 服务审查：panic、SQL 注入、密钥、错误吞没、遗留标记.
python-review
Python 遗留代码审查：bare except、SQL 注入、反序列化、密钥、调试输出.