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-review-edge-case-huntergit 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-review-edge-case-hunter)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-review-edge-case-hunter"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-review-edge-case-hunter/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-review-edge-case-hunter"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-review-edge-case-hunter.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 | $0.00071 | $0.00585 |
| Opus 5 | $0.00036 | $0.00293 |
| Sonnet 5 | $0.00014 | $0.00117 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
speclite-review-edge-case-hunter 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 7d 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
[技能说明] Speclite Edge Case Hunter 是纯路径追踪审查器，只列出未处理的边界条件和分支路径。它不评论代码好坏，不输出解释性废话；当输入 diff 时只扫描 diff hunks 直接可达的边界。
[核心能力] - 范围识别：识别输入是 diff、完整文件还是函数，确定审查范围。 - 路径枚举：机械遍历控制流、循环、错误处理、early return 和领域边界。 - 边界推导：从内容本身推导 null、empty、off-by-one、overflow、timeout、race 等边界类别。 - 仅报未处理：已处理路径静默丢弃，只保留缺失 guard 的发现。 - 完整性复查：回看每类边界，补充遗漏发现。 - 严格 JSON 输出：只返回符合 schema 的 JSON array。
[执行流程]
1. 从用户输入读取 content；为空或不可解码时返回固定 JSON 错误数组并停止。
2. 识别内容类型并确定范围；diff 只看 changed hunks 直接可达边界。
3. 穷举范围内所有 branching path 和 boundary condition。
4. 判断每条路径是否已有显式处理；只收集未处理路径。
5. 复查所有 edge class，补充遗漏并丢弃已处理项。
6. 输出 JSON array；每项只包含 location、trigger_condition、guard_snippet、potential_consequence。
[注意事项]
- 输出必须是 JSON array，不要加 Markdown 包裹或解释文字。
- trigger_condition 和 potential_consequence 各不超过 15 个词。
- guard_snippet 必须是单行字符串，不含未转义换行或引号。
- 空数组 [] 表示没有发现未处理路径，是有效结果。
- 不要审查范围外代码，除非输入内容显式引用外部函数。
What ships with it
1 file 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.
- 7d ago First seen · 36 lines · 71 tokens per session scan A b55906c5a811
speclite-review-edge-case-hunter is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 585 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
omc-review
Evaluate finished work for defects, risk, and simplification before it ships.
project-check
Existing project health scan — audits Infrastructure, Security, Quality, and Harness setup. Read-only. Use when: '/project-check', 'project health check', 'project audit', 'what\'s missing', 'analyze my project', 'check setup'. Ends with /project-init and /setup recommendations. NOT for new projects (use…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
ase-code-lint
Lint source code for potential code quality problems. Use when the user wants to "lint" or "check" source code.
full-audit
Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) ->…