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 agentmods add skills/himanshu-sangshetti/cursor-stack/plan-engnpx skills add Himanshu-Sangshetti/cursor-stack --skill plan-enggit clone --depth 1 https://github.com/Himanshu-Sangshetti/cursor-stackWrote 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/himanshu-sangshetti/cursor-stack/plan-eng)<a href="https://agentmods.dev/skills/himanshu-sangshetti/cursor-stack/plan-eng"><img src="https://agentmods.dev/badge/skills/himanshu-sangshetti/cursor-stack/plan-eng.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 | $0.00044 | $0.01643 |
| Opus 5 | $0.00022 | $0.00822 |
| Sonnet 5 | $0.00009 | $0.00329 |
| Haiku 4.5 | $0.00004 | $0.00164 |
Grade A, and why
plan-eng 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Eng Review - Tech Lead Mode
Handoff from plan-ceo
Best used in the same chat as plan-ceo so it can consume the product direction.
Project overrides: If @cursor-stack or AGENTS.md contains a cursor-stack section (mainBranch, testCommand, complexityThreshold, branchPrefix, etc.), apply those values. Use them for git commands, complexity checks, and any project-specific thresholds.
If researcher output exists in the conversation, use its Research Brief: codebase findings, technical options, and key questions to inform architecture and tradeoff decisions.
Assume plan-ceo has been run. The product direction, 10-star version (or minimal version), and mode (EXPANSION / HOLD / REDUCTION) are set. Your job is to create the technical execution plan that implements that direction.
- If plan-ceo output exists in the conversation, use it. Build on: Recommendation, 10-star version, NOT in scope, What already exists, Dream state delta.
- If not, infer product direction from the user's description.
Your Mindset
Think like a senior tech lead or staff engineer:
- How do we build this reliably and maintainably?
- What are all the edge cases and failure modes?
- What would cause an on-call page at 3am?
Engineering Preferences
Use these to guide all recommendations:
- DRY — flag repetition aggressively
- Well-tested — prefer more tests over fewer
- "Engineered enough" — not under- or over-engineered
- Explicit over clever
- Minimal diff — fewest new abstractions and files touched
- Observability — logs, metrics, traces for new codepaths
- Security — threat model for new paths
Step 0: Scope Challenge (before architecture)
Before creating the technical spec, answer:
- What existing code already partially or fully solves each sub-problem? Can we capture outputs from existing flows rather than building parallel ones?
- What is the minimum set of changes that achieves the stated goal? Flag any work that could be deferred without blocking the core objective. Be ruthless about scope creep.
- Complexity check: If the plan touches more than 8 files or introduces more than 2 new classes/services, treat that as a smell and challenge whether the same goal can be achieved with fewer moving parts.
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.
- 4d ago First seen · 203 lines · 44 tokens per session scan A e122a81fbc95
plan-eng is a skill published in the GitHub repository Himanshu-Sangshetti/cursor-stack (6 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 1,643 once invoked, about $0.0002 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
deep-research
Iterative multi-source investigation with contradiction logging—use for audits, vendor comparisons, security posture reviews, benchmarking methodology, literature surveys, ambiguous technical history, regulated domains, unfamiliar APIs, architectural landscape scans, falsifiable claims needing citations, stakeholder…
frontend-brand
他山前端品牌设计系统完整参考手册。包含技术框架选型、设计令牌(颜色/字体/圆角/阴影)、组件规范代码模板、响应式/无障碍约定。被 role-前端开发 和 role-UI设计师 主动调用;与 frontend-brand-guard.mdc(约束层)配套使用。.
research-output
对任何主题进行系统调研,自动产出图文并茂的 Markdown 文档(含 Mermaid 结构图 + qwen-image 可视化),保存到认知结构对应维度的知识库,并自动注册到文档分类清单和知识图谱。当用户说「帮我调研/调研一下/系统调研/研究一下/帮我系统了解/深度研究 [主题]」时触发。.
cognitive-reorganize
从整个工作区出发,系统性地重组认知结构并整理全局文档归属。适用于首次建立认知结构、或积累了大量散落文档需要批量归档时。基于三大闭环框架(Loop1 Skill体系 / Loop2 思维体系 / Loop3 场景投射)做全工作区分类路由。触发词:「系统整理」「重组认知结构」「从文档构建认知结构」「整合文档」「全量梳理」「认知结构乱了」「全工作区整理」「文档归属梳理」「如何加入认知结构」「怎么加入认知结构」「按规范加入」「未更新的文档怎么处理」「这些文档要怎么整理」「有没有关于X的已有文档」。注意:若用户仅询问流程而非执行重组,执行 Step 0.5(检查分类清单现状)后,先向用户展示已有文档状态和分类建议,再确认是否执行完整重组。.
project-backlog
项目待办管理器(两种模式)。【收集模式】接收任意混合输入 → 解析追加到「项目待办.md」文档,不立即执行;【处理模式】读取文档 → 前置决策收集 → 按优先级逐条路由执行 → 更新状态 → 批次报告。触发词:【收集】「有几个问题先记到待办」「加到项目待办」「先存到待办文档」「记录这些待办」;【处理】「处理项目待办」「按待办文档逐条修复」「开始处理待办文档」。⚠️ 触发词必须含「待办」关键词才激活,避免与 issue-tracker / bug-fix-loop 混淆。.
skill-capture-closure
任务结束后的统一复盘入口,同时覆盖「修改」(识别并修复 B/K 对象缺陷)和「沉淀」(将新经验/洞见写入对应 B/K 对象)两个方向。主分类轴:B-object(Skill/Rule/Agent)vs K-object(原则/框架/规范/项目规格/碎片),操作类型:modify(修改已有)或 create(新建沉淀)。触发词:「复盘一下」「做个复盘」「这次踩坑了」「这个经验值得记」「跑通了」「总结经验」「沉淀一下」「记录一下这次」。注意:项目级批量复盘请触发 project-retrospective。.