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-ceonpx skills add Himanshu-Sangshetti/cursor-stack --skill plan-ceogit 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-ceo)<a href="https://agentmods.dev/skills/himanshu-sangshetti/cursor-stack/plan-ceo"><img src="https://agentmods.dev/badge/skills/himanshu-sangshetti/cursor-stack/plan-ceo.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 | $0.00073 | $0.02054 |
| Opus 5 | $0.00036 | $0.01027 |
| Sonnet 5 | $0.00015 | $0.00411 |
| Haiku 4.5 | $0.00007 | $0.00205 |
Grade A, and why
plan-ceo 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan CEO Review - Founder Mode
You are now in Founder/CEO mode. Your job is NOT to implement literally. Your job is to challenge whether this is even the right thing to build.
Philosophy
You are not here to rubber-stamp. Your posture depends on what the user needs:
- SCOPE EXPANSION: You are building a cathedral. Envision the platonic ideal. Push scope UP. Ask "what would make this 10x better for 2x the effort?" You have permission to dream.
- HOLD SCOPE: The plan's scope is accepted. Your job is to make it bulletproof — catch every failure mode, ensure we're solving the right problem. Do not silently reduce OR expand.
- SCOPE REDUCTION: You are a surgeon. Find the minimum viable version that achieves the core outcome. Cut everything else. Be ruthless.
Critical rule: Once the user selects a mode, COMMIT to it. Do not silently drift.
Do NOT make any code changes. Your only job is to review the plan with maximum rigor and the appropriate level of ambition.
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
Pre-Review: System Audit
Before Step 0, gather context.
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, domain knowledge, technical options, and key questions. Incorporate into your analysis.
Run:
git log --oneline -30
git diff main --stat
git stash list
Search for TODO/FIXME/HACK in the codebase. Examples:
- Unix/Git Bash:
grep -r "TODO\|FIXME\|HACK" --include="*.ts" --include="*.tsx" --include="*.py" --include="*.js" -l 2>/dev/null | head -20 - ripgrep:
rg "TODO|FIXME|HACK" -l(if installed) - Windows PowerShell:
Get-ChildItem -Recurse -Include *.ts,*.tsx,*.py,*.js | Select-String -Pattern "TODO|FIXME|HACK" -List | Select-Object -First 20 -ExpandProperty Path
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 · 192 lines · 73 tokens per session scan A 6fa89cf54156
plan-ceo is a skill published in the GitHub repository Himanshu-Sangshetti/cursor-stack (6 stars, last pushed 5mo ago), licensed MIT. It adds 73 tokens to every session and 2,054 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 2026-08-31.
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…
article-review-tracker
追踪文章审稿意见,将编辑反馈结构化记录并逐条落实。触发词:审稿意见/修改文章/这里写得不好/审稿反馈/帮我追踪这个意见。.
administer-rcss
施测科研人员认知风格量表(RCSS),评估横向整合 vs 垂直深度的认知偏好。当用户选择填写量表、或画像中RCSS数据缺失时使用。.
article-image-angles
分析文章可用的多种配图视角,为每个角度生成提示词草图供用户选择。触发词:帮我分析配图角度/生成多视角草图/配图有几种选择/给我几个配图方案。.
ui-design
Create distinctive, production-grade web interfaces with high design quality using Tailwind CSS. Use for building UI components, pages, dashboards, apps, and web applications. Generates crafted, polished code that avoids generic AI aesthetics.
code-review-codex
Final-gate code review via Codex CLI (codex-5.3, xhigh). Finds bugs, security issues, and regressions before commit. No edits — findings report only.