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 TNT-Likely/honeycomb --skill analyze-issuegit clone --depth 1 https://github.com/TNT-Likely/honeycombWrote 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/tnt-likely/honeycomb/analyze-issue)<a href="https://agentmods.dev/skills/tnt-likely/honeycomb/analyze-issue"><img src="https://agentmods.dev/badge/skills/tnt-likely/honeycomb/analyze-issue.svg" alt="Measured on agentmods" 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 | $0.00166 | $0.01195 |
| Opus 5 | $0.00083 | $0.00598 |
| Sonnet 5 | $0.00033 | $0.00239 |
| Haiku 4.5 | $0.00017 | $0.00120 |
Grade A, and why
analyze-github-issue 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
单 Issue 深度分析技能
做什么
对一条 GitHub issue 做透彻分析,回答四个问题:
- 是不是真问题? —— bug 真实存在 / 使用误解 / 已被修复 / 无法复现
- 要不要修 / 要不要做?
- 优先级多高? 4.(功能请求)合理吗?契合产品吗?
和 github-issue-triage 技能互补:triage 是宏观全量排序,本技能是单点深挖。常见组合:triage 选出可疑/高价值的,再用本技能逐个做透。
流程
1. 拉取 issue 全文
env -u HTTPS_PROXY -u HTTP_PROXY -u https_proxy -u http_proxy -u ALL_PROXY -u all_proxy \
gh issue view N --repo OWNER/REPO \
--json number,title,body,labels,comments,reactionGroups,state,author
读完整 body 加所有评论 —— 评论里常有复现补充、维护者回应、重复线索、版本信息。
2. 判类型
bug / 功能请求 / question(使用问题) / 重复 / 信息不足。先定性,再走对应分支。
3a. 如果是 Bug —— 必须用代码验证,别只信描述
- 在 codebase 定位相关代码,确认 bug 真实存在(找到会出错的那几行)
- 讲清:根因(哪行、为什么错)、影响面(谁会中招、多频繁)、能否复现(给最小路径)、是否已被其它改动修掉
- 区分:真 bug / 配置或使用问题 / 环境特定 / 描述不实
- 危害分级:数据正确性错误、崩溃 最高;偶发体验问题低
- 给是否需要修的明确结论 + 修复思路 + 工作量(S/M/L)
实战参照:有的 issue 报"AI 解析失败",定位到
amount as num?强转字符串直接崩 —— 真 bug,可定位可修;有的报"自动记账没反应"实为通知权限没开 —— 使用问题,引导即可,不动代码。结论必须落到代码或事实,不能凭描述拍脑袋。
3b. 如果是功能请求 —— 评估合理性,而非照单全收
- 契合度:符合产品定位与现有信息架构吗?会不会把 app 撑成四不像?
- 普遍 vs 小众:看呼声(👍/💬)+ 是不是只有提出者一个人的特殊流程
- 已有替代:现有功能能否绕过 / 组合实现?
- 可行性 / 成本:技术工作量?有无平台 / 合规限制(如某些权限上架受限)
- 拆分:大需求拆成"先做最痛的小核心"
- 结论:建议做 / 可做但不急 / 不建议做(给理由)/ 需求方补充信息
4. 输出结构
## #N <标题>
- 类型:bug / feature / question / …
- 结论:<真 bug 建议修 / 合理,P1 建议做 / 使用问题,引导即可 / 不建议做:…>
- 依据:<代码定位 file:line / 呼声 / 契合度分析>
- 优先级:🔴P0 / 🟡P1 / 🟢P2 / ⚪P3 + 一句理由
- 工作量:S / M / L
- 下一步:<修复思路 / 拆分方案 / 要追问的信息>
可直接作为 issue 评论草稿交给用户,但不自动发评论、不改 issue 状态。
红线
- bug 结论必须有代码依据 —— 不能只凭 issue 描述断言"是 bug"
- 功能请求诚实评估,该说"不建议做"就说清理由 —— 不当老好人照单全收
- 只读:不自动评论 / 关闭 / 改 label,产出供人决策
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 · 73 lines · 166 tokens per session scan A 4c14a127ac63
analyze-github-issue is a skill published in the GitHub repository TNT-Likely/honeycomb (2 stars, last pushed 7d ago), licensed MIT. It adds 166 tokens to every session and 1,195 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
mobile-flows-maestro
This skill should be used when Maestro is explicitly requested or already present and the task is to author, run, or debug iOS/Android Maestro flows; use Maestro MCP; or handle Maestro selectors, system UI, permissions, Keychain, JavaScript, waits, device state, flakiness, or CI. Evidence includes a .maestro directory…
esp32-expert
This skill should be used for ESP32-specific hardware and runtime work in ESP-IDF, Arduino-ESP32, or PlatformIO projects: target/build detection, FreeRTOS tasks and ISRs, memory/DMA, peripherals, power, networking/security, OTA, crash diagnosis, and unattended reliability. Trigger on "debug this ESP32 crash", "review…
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
roslyn-query
Query .NET/C# codebases using Roslyn AST analysis via dotnet run file. Use for tracing data flow, auditing API usage, finding pattern violations, or ad-hoc codebase queries.
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).