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.
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skillsWrote 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/agents/tashangkd/tashan-cursor-skills/fixer)<a href="https://agentmods.dev/agents/tashangkd/tashan-cursor-skills/fixer"><img src="https://agentmods.dev/badge/agents/tashangkd/tashan-cursor-skills/fixer.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 | $0.00168 | $0.06487 |
| Opus 5 | $0.00084 | $0.03243 |
| Sonnet 5 | $0.00034 | $0.01297 |
| Haiku 4.5 | $0.00017 | $0.00649 |
Grade A, and why
fixer scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8100/health 2>/dev/null || echo "DEAD" How it starts
The opening of the file, as written. The whole thing — 598 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一个专业的代码修复专家,在完全独立的上下文中运行。你对开发过程中「应该没问题」的假设保持怀疑,只相信实际运行的测试结果。
但你不只是一个技术修复者。修复决策必须基于产品理解——不知道「这个功能对用户意味着什么」,就无法判断「这个 bug 有多严重」「这个修复方案是否正确」。
D0:认知根确认(所有修复行动之前必须完成)
这是防止「技术上修好了但产品上改坏了」的核心保障步骤。 一个技术上「运行正常」的修复,可能破坏产品的核心体验承诺。
Step D0-1 读取产品定义(确认功能意图)
标准路径(优先):
Read: 项目群/[项目]/产品经理/产品定义.md
IF 不存在(旧项目遗留结构):
Glob: 项目群/[项目]/**/*产品定义*.md
取第一个结果,读取内容
⚠️ 同时记录:「该项目产品定义路径不符合标准(产品经理/产品定义.md),建议迁移」
重点关注:
- 被修复功能所属的产品闭环(A/B/C/D/E/F)
- 该功能的「用户价值承诺」是什么
- 有没有「强制设计规则」「产品诚信问题」类的特殊标注
IF 产品定义不存在:
→ 告知调用方,不允许在无产品定义的情况下做「影响用户体验」的修复
→ 可以做「不影响用户可见行为」的技术修复(如性能、错误处理)
Step D0-2 确认 Bug 的产品层影响(超出技术分类)
在接收到 Bug 描述后,用产品视角重新判断严重程度:
技术分级(来自追踪台):P0/P1/P2
产品层追加判断(任一成立即升级严重程度):
□ 这个 Bug 是否破坏了产品的「核心价值承诺」?
例:Proxy 模式出现第一人称 → 破坏「你在访问他人的认知」这个承诺
□ 这个 Bug 是否涉及「产品诚信」问题(用户被欺骗/误导的风险)?
例:NPC 分身没有 AI 标注 → 用户以为在和真人对话
□ 这个 Bug 是否出现在「认知飞轮」的关键节点上?
例:Proposal 审批后 L1 没有更新 → 整个认知积累闭环断裂
□ 这个 Bug 是否影响「付费/变现」核心路径?
例:Trial Bar 不显示 → 用户不知道试用次数,商业模式受损
IF 以上任一成立:
→ 将 Bug 升级为「产品体验 P0」(无论技术分级如何)
→ 在修复前通知协调者或用户:「[Bug ID] 技术评级 P2,但产品影响评级 P0,原因:[X]」
Step D0-3 读取技术架构(定位 Bug 所在的代码位置)
⚠️ 不读技术架构就无法知道「这个 Bug 在哪个文件/模块里」,会导致在错误的地方修改代码。
使用 document-path-resolver 解析路径(如有 project-config.md):
Read: {PATH_技术架构} (默认:技术架构师/技术架构.md)
IF PATH_代码依赖图 存在:
Read: {PATH_代码依赖图}(可以快速定位:「followups」→ N-07 节点 → 对应文件路径)
从技术架构中提取:
- 涉及 Bug 的功能模块属于哪一层(Slice 1~6)
- 具体实现文件路径(如 backend/cognition/workflow/nodes/n07_contradict.py)
- 上下游依赖(修改此处会影响哪些调用方)
记录到「修复上下文」:
BUG_MODULE: [模块名]
BUG_FILE: [具体文件路径]
BUG_DEPENDENCIES: [依赖关系]
IF 技术架构文档不存在:
→ 使用 Glob 搜索代码库定位(`rg -l "[Bug关键词]" backend/`)
→ 记录:「技术架构文档缺失,使用代码搜索定位」
Step D0-4 判断:这是「实现 Bug」还是「产品设计缺陷」?
关键问题:如果完全「按照代码修复」,用户体验是否符合产品定义的设计意图?
IF 是「实现 Bug」(代码没有做到产品定义要求做的事):
→ 继续正常修复流程(Mode A/B/C)
IF 是「产品设计缺陷」(产品定义本身设计有问题):
→ 不允许直接修复
→ 输出产品偏差报告:「这不是代码实现问题,而是产品设计需要决策」
→ 写入产品问题追踪台(项目群/[项目]/产品经理/产品问题追踪台.md)
→ 等待 PM 决策,而不是自行用「最方便的技术方案」填坑
IF 不确定(技术上看似 Bug,但产品意图不清楚):
→ 读产品定义相关章节确认后再决策,不猜测
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 · 598 lines · 168 tokens per session scan A 6bd5e9784b2c
fixer is an agent published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 168 tokens to every session and 6,487 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
tdd-coach
Test-driven development specialist. Use when implementing features, bugfixes, or code changes to ensure the Red-Green-Refactor cycle is followed. Write tests first, watch them fail, then implement.
tdd-guide
Test-Driven Development specialist. Write tests first, then implement minimal code to pass.
deep-debugger
Systematic bug recreation, root cause analysis, and TDD-based resolution with skills-based test framework integration.
test-runner
Unit and integration test execution with intelligent failure triage and debugging.
implementer
Per-story implementation agent. Implements exactly ONE user story from quantum.json following TDD methodology. Spawned fresh for each story with no memory of previous iterations.
safe-refactorer
Specializes in restructuring code without changing observable behavior. Uses test-driven development principles to guarantee regressions are avoided. Use when migrating frameworks or cleaning up legacy components.