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 skills add flanliulf/SpecLite --skill speclite-flow-gategit clone --depth 1 https://github.com/flanliulf/SpecLiteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/flanliulf/speclite/speclite-flow-gate)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-flow-gate"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-flow-gate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-flow-gate"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-flow-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00081 | $0.00883 |
| Opus 5 | $0.00041 | $0.00441 |
| Sonnet 5 | $0.00016 | $0.00177 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
speclite-flow-gate 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 8d 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.
What it actually says
[Overview（技能说明）]
SpecLite 实现阶段流程门控 Skill，用于在 Story/Epic 启动或完成时检查 planning contract、实际源码实现和测试证据是否一致，避免等到 speclite-dev-story 执行中途才 HALT。
[Core Capabilities（核心能力）]
- Mode 驱动门控：支持 story-kickoff、story-completion、epic-completion、epic-kickoff 四种检查模式。
- Anchor 分类：区分 Contract Anchor、Functional Anchor、Evidence Anchor 和 Guidance Anchor，禁止把未契约化文件名当成唯一 hard gate。
- 等价实现裁决：当实现形态偏离 Story guidance 但 owning SPEC、源码路径和测试证据成立时，输出 PASS_EQUIVALENT。
- 失败类型定位：用 FAIL_CONTRACT、FAIL_FUNCTION、FAIL_EVIDENCE、DECISION_NEEDED 精确说明阻断原因。
- 报告生成：把 gate report 写入 {implementation_artifacts}/flow-gates/，供 sprint-status、dev-story、CR 和 finalizer 消费。
- 流转建议：给出下一步动作，例如继续 dev-story、修订 Story、补测试证据、或先运行 Epic completion gate。
[Workflow（执行流程）]
1. 完整阅读 references/workflow-details.md；该文件是四种 gate mode、结果枚举、报告格式和 HALT 规则的权威定义。遇到等价实现或固定路径歧义时，同时读取 references/regression-scenarios.md。
2. 解析目标 mode 与目标对象：Story key、Story 文件路径、Epic 编号或下一 Epic 编号。
3. 加载 merged runtime config、sprint-status.yaml、目标 Story/Epic、owning SPECs、相关源码和测试证据。
4. 按 Contract -> Functional -> Evidence -> Guidance 顺序做门控判断，并生成 assets/report-template.md 规定的报告。
5. 只有 PASS 或 PASS_EQUIVALENT 允许后续 workflow 继续；其他结果必须先修正文档、实现或证据。
[Notes（注意事项）]
- 固定文件名只有在 owning SPEC 明确指定时才是 hard gate；否则必须先检查等价 functional implementation 和测试证据。
- 本 Skill 只生成 gate report，不修改源码、不推进 Story/Epic 状态、不替代 CR。
- 报告必须写入 {implementation_artifacts}/flow-gates/，文件名按 mode 和目标对象稳定生成。
- 报告开头的 YAML frontmatter 是 downstream hook、dev-story、CR 和 finalizer 的 machine-readable source；不得要求消费者解析 Markdown prose 判断 gate result。
- Guidance Anchor mismatch 不能直接判定 blocked；只能在确认 contract/function/evidence 缺失后输出失败。
- 中英文入口必须同步更新；新增 mode 或结果枚举时同步更新 references/workflow-details.md。
[Generation Metadata（生成信息）] 本 Skill 由 speclite-skill-creator 自动生成。如需修改，必须同步更新 SKILL.md 与 SKILL.en.md，并通过 skills-upgrade 管理版本。
What ships with it
7 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.
- 8d ago First seen · 39 lines · 81 tokens per session scan A f532dcfb1017
speclite-flow-gate is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 883 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
Backend Test Patterns
Guidance for covering the failure and edge paths of a backend change — bad input, concurrent writes, partial failure — not just the happy path.
Visual Verification Workflow
The procedure for actually confirming a UI change in a real or preview browser — golden path, an edge case, console errors, and responsive/dark-mode checks — before calling it done.
Test Patterns
What "well-tested" actually means — covering edge cases and failure modes deliberately, not just confirming the happy path runs once.
Regression Discipline
The rule that every bug fix ships with a test that fails on the old code and passes on the new — and how to write that test well.
Test Automation
Patterns for keeping the test suite fast, deterministic, and runnable in CI — mocking rules, isolation, and flakiness prevention.
Test Strategy
How to decide what to test at what level — the test pyramid, risk-based coverage, and matching test depth to change risk.