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-plannpx skills add friedbotstudio/baseline --skill sprint-plangit 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 | $0.00093 | $0.00885 |
| Opus 5 | $0.00046 | $0.00443 |
| Sonnet 5 | $0.00019 | $0.00177 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
sprint-plan 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sprint-plan — author a sprint manifest with per-feature done-criteria
sprint-plan turns an MVP vision into a sprint manifest: a prioritized list of features, each carrying the done-criteria that make "done" mechanically checkable. The manifest is the input contract for sprint-oracle, which fails a sprint until every feature meets its criteria. This is Slice A of the mvp-sprint-parallel-cycles epic — the completeness half of the parallel-sprint goal (a sprint can be fast yet provably not partial).
What the manifest is
A JSON document (template-manifest.json is the shape). Each feature declares three done-criteria dimensions so completeness is a grep, not a judgment call:
done_record— a reference proving the feature is specified (a spec AC id, e.g.AC-012). Non-empty.edge_tests— names of tests covering error / empty / edge states. A non-empty array.wiring_test— the name of one integration test exercising the feature end-to-end.
{
"sprint": "<sprint name>",
"features": [
{
"id": "search",
"priority": "P0",
"done_record": "AC-012",
"edge_tests": ["search_empty_query", "search_unicode"],
"wiring_test": "search_end_to_end"
}
]
}
The test-tag convention (how sprint-oracle resolves the names)
A named test counts toward a feature only when the test file tags it. Immediately above the test('<name>', …) call, place:
// @sprint-feature:<feature-id> @kind:edge|wiring|happy
test('<name>', () => { /* … */ });
sprint-oracle builds a map of testName → {feature, kind} from these tags and resolves each manifest reference against it. A test tagged @kind:happy does not satisfy an edge or wiring requirement — that is the deliberate, mechanical line (no script can prove a test is semantically an edge case; the tag is the author's crisp claim, and the oracle verifies the claim resolves).
How to use
- Decompose the MVP vision into features. Decide priority (
P0/P1/…) per feature — scoping, not implementation. - For each feature, name its
done_record(the spec AC it traces to), theedge_testsit must carry, and itswiring_test. - Write the manifest (default location:
.claude/state/sprint/<sprint>/manifest.json, gitignored runtime state). - Validate the shape before handing it to the oracle:
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 · 64 lines · 93 tokens per session scan A 011418d202fd
sprint-plan is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 93 tokens to every session and 885 once invoked, about $0.0005 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.