issue

issue is a skill for Claude Code from XRenSiu/claude-code-forge. It costs 283 tokens per session (2,534 once invoked), scanned A, original, MIT.

A GitHub issue-writing workflow turns a request, bug, or escaped defect into a structured task with testable acceptance conditions. It checks the draft before asking permission to create the public issue.

In plain words
What is it for?
Use it to create feature, bug, or escaped-defect issues, decide whether a request needs product clarification or can go straight to implementation, and prepare an issue for mechanical checking.
Why use it?
Vague phrases such as “make search faster” can be accepted by almost any implementation and give later reviewers no clear target. This workflow makes the expected result, scope, assumptions, and confirmation step explicit.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the sdlc plugin — 14 skills, 5 agents shipped together

Good fit Use it to create feature, bug, or escaped-defect issues, decide whether a…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xrensiu/claude-code-forge/issue
Install

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.

Any agent
npx skills add XRenSiu/claude-code-forge --skill issue
Clone the repo
git clone --depth 1 https://github.com/XRenSiu/claude-code-forge

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 14 skills, 5 agents.

Wrote 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.

agentmods badge for issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/issue.svg)](https://agentmods.dev/skills/xrensiu/claude-code-forge/issue)
Your own site
<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/issue"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/issue.svg" alt="Measured on agentmods" height="20"></a>
Per session 283 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,534 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00283 $0.02534
Opus 5 $0.00142 $0.01267
Sonnet 5 $0.00057 $0.00507
Haiku 4.5 $0.00028 $0.00253

Measured yesterday against content hash 0053db4d6b30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify_issue.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/sdlc/skills/issue/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

issue — 愿望变成能判真假的条目

产物是一条 GitHub issue,其 body 按 assets/issue_template.md 的段落序呈现(这是产物序—— 第 5 格——出口可检,不是流程)。本文件写:issue 在世界里是什么、什么算写对、原语与出口、 建之前的门。怎么问、怎么组织材料是你的份额。

缺口(Judgment + Capability + Control)

deletion 测试:撤掉本 skill,引擎会把需求原文当 body 直接建 issue——"让搜索更快""把审核做对"。 这样的 issue 任何实现都能"通过",下游 done_when 没有源头,review 判"越界"没有基准。缺的是 判据(可证伪长什么样)、原语(verify_issue.py 把判据的机械半边编译掉)、 (建 issue 是公开动作:先给人看)。

世界(Σ)

  • issue 是 TASK 的雏形,不是契约本身。 契约(done_when.yaml v2)由 /acceptance-spec 或 /sdlc 从这里的 AC 内联生成;issue 里的 AC 已经是 v2 形状,所以两边不会漂移。
  • 三种入口,同一模板:feature(需求)、bug(复现 + 期望 + 实际,AC 就是"复现不再 发生"+ 回归守卫)、escape(合入后发现的缺陷:多一段"归因层 / 为什么该层的门没拦住", 同时追加到 escape-defects.md——它是世界层唯一的外部校准源)。
  • 两条轨道。 语义份额 × 变化率高、实现原语难度低 → PSL 轨(先 /psl 建世界 → G1 人签, 再回来建 issue);确定性主导 → TASK 轨直接建。混合需求只对体验性内核走 PSL。速判:把需求 交给不了解产品的工程师照字面做,会不会做出"技术正确、产品错误"的东西?会 → PSL。 客观触发--dos dos.yaml 时,依赖 DOS: 字段里出现 dos.yaml 解析不了的概念 → 强制 PSL 轨(脚本判,不靠自评)。详见 references/dual-track.md
  • 范围段四项(做 / 不做 / 硬约束 / 成功度量)是人写的:"做到哪儿为止"agent 推不出来。 你可以起草,但每项都要让用户确认或改。
  • 假设台账:澄清最多 3 轮;答不上来的承重槽不默认填,写进台账:假设 · 绑定的 REQ/AC · 风险 · 到期验证点(哪个 AC 或哪道门验证它)。超时不是失败,是带风险签字继续。
  • 关于用户的 Σ:"快一点""稳定""大部分"是日常语言,不是判据——把它翻译成数字时,数字 的来源要么是用户给的、要么是 SLO/KPI、要么是一次真实失败;没有来源就 needs_threshold_source 标出来问,不编。

判据(φ):什么算写对了

  • 可证伪或不进:AC 的 expect / statement 里出现模糊量词(快 / 慢 / 稳定 / 大部分 / 合理 / 友好 / fast / reliable / most / better…)而没有数字阈值 → 不是验收条件。
  • happy 带 unhappy 孪生:每条事件型 AC("当 X 时系统应 Y")配一条 unwanted("当 <边界 / 恶意 / 失败输入> 时系统应 <拒绝 / 降级 / 报错>")。未定义的失败语义正是被钻的缝。
  • AC v2 形状kind: mechanical 必有 observe(route / cli / ui data-test / db_field / event)
    • given + expectkind: human 必有 statement + judge ∈ {product, design, tech} + evidence ∈ {checklist, demo}。详见 references/acceptance-shape.md
  • observe 是观察边界,不是实现结构:出现 src/….ts/.py/… 文件名、函数名 → 拒(契约不该 规定实现结构;文件级存在性下放到任务卡)。
  • 范围四项非空轨道已判定(psl | task);依赖 DOS 字段存在(可为 none,但要写)。
  • bug 类:复现步骤 ≥ 1 条、期望 vs 实际都在、至少一条 AC 是回归守卫。
  • escape 类:归因层 ∈ {card, plan, task, ontology, world} + "为什么该层的门没拦住"一句。
  • 残差(机器不判,路由到人):这些 AC 是不是这次最窄的可证伪条件;阈值是否反映 KPI 而非 空气;unhappy 孪生盖的是不是对的边。脚本给 needs_semantic_review,不裁决。

Read the full file on GitHub · 115 lines

Changes

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.

  1. yesterday First seen · 115 lines · 283 tokens per session scan A 0053db4d6b30

Subscribe to this mod's changes

issue is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed yesterday), licensed MIT. It adds 283 tokens to every session and 2,534 once invoked, about $0.0014 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 2026-09-05.