Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add titusz/skills/plugin install evaluate-startupWrote 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/titusz/skills/evaluate-startup)<a href="https://agentmods.dev/skills/titusz/skills/evaluate-startup"><img src="https://agentmods.dev/badge/skills/titusz/skills/evaluate-startup.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 | $0.00156 | $0.02072 |
| Opus 5 | $0.00078 | $0.01036 |
| Sonnet 5 | $0.00031 | $0.00414 |
| Haiku 4.5 | $0.00016 | $0.00207 |
Grade A, and why
evaluate-startup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate Startup
Turn a raw startup idea into an evidence-backed, scored evaluation with a durable, browsable artifact trail. The output is a decision aid, not a cheerleading document: honest scores, falsifiable assumptions, explicit kill criteria.
Tooling
All validate/render/index commands below use the bundled script:
uv run "${CLAUDE_PLUGIN_ROOT}/skills/evaluate-startup/scripts/render.py" <command> ...
Abbreviated as render.py in the phases. If ${CLAUDE_PLUGIN_ROOT} is not set in your
environment, resolve the script path relative to this SKILL.md file.
Arguments
$ARGUMENTS may contain, in free-form order (all optional):
- Idea description — anything from a one-liner to a full pitch. If absent, ask for it.
- Output path — e.g.
--out ./somewhereor "store results in X". Default:./startup-ideas - Custom instructions — e.g.
--instructions "..."or natural language like "focus on the EU market" or "add a competitor pricing matrix to the report". These tailor the interview, research angles, scoring weights, and report extras.
Interpret naturally; do not demand exact flag syntax.
Output layout
<output-root>/
├── index.html # searchable card index (auto-regenerated)
└── <idea-slug>/
├── analysis.json # canonical latest evaluation
├── report.html # rendered standalone report
└── history/ # prior runs, timestamped (on re-evaluation)
└── analysis-20260806T120000Z.json
Slug: lowercase, hyphenated, from the idea name (e.g. "Freight Invoice Audit Agent" →
freight-invoice-audit-agent). If a directory with analysis.json already exists for
this idea, this is a re-evaluation: move the old analysis.json into history/
before writing the new one. Never silently overwrite an evaluation.
The archive filename is analysis-<stamp>.json, where <stamp> is the old file's
evaluated_at with - and : stripped (2026-08-06T12:00:00Z → 20260806T120000Z).
Colons are illegal in Windows filenames, so never use the raw RFC 3339 value.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 186 lines · 156 tokens per session scan A e5d04dddad20
evaluate-startup is a skill published in the GitHub repository titusz/skills (2 stars, last pushed 13d ago), licensed MIT. It adds 156 tokens to every session and 2,072 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…