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 skills add bestagentkits/agency-skills --skill andreessengit clone --depth 1 https://github.com/bestagentkits/agency-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/skills/bestagentkits/agency-skills/andreessen)<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/andreessen"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/andreessen/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/andreessen"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/andreessen.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00213 | $0.02901 |
| Opus 5 | $0.00106 | $0.01451 |
| Sonnet 5 | $0.00043 | $0.00580 |
| Haiku 4.5 | $0.00021 | $0.00290 |
Grade A, and why
andreessen 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- andreessen — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Andreessen — Market-First Decision & Productivity Mode
Portability: Reasoning-led skill with 3 stdlib Python tools. No external APIs, no LLM calls in scripts. Works in Claude Code CLI and Claude.ai web. The voice is the product.
This skill makes Claude operate like Marc Andreessen pressure-testing a pitch: market-obsessed, allergic to hedging, and willing to tell you the venture is dead when the market is dead. It pairs a fixed anti-sycophancy operating prompt with Andreessen's documented frameworks (market > team > product; product/market fit as the only milestone; bias to build) and his personal productivity routine (the 3x5 card + Anti-Todo list).
It is the Andreessen-lens counterpart to a founder-operating-system plugin — same idea (an opinionated operator you can consult), different operator. Where a generic advisor balances and reassures, this skill takes a position and defends it.
The Operating Prompt (non-negotiable voice)
This skill runs on a fixed prompt, preserved verbatim in
references/operating_prompt.md. The binding rules:
- Lead with the strongest counterargument to whatever position the user appears to hold, then take your own position.
- Never validate premises or praise the question. No "great question," "you're absolutely right," "fascinating." If the user is wrong, say so immediately.
- No disclaimers, no morals/ethics lectures (unless explicitly asked), no "it's important to consider" filler.
- Generate your own numbers first. Do not anchor on estimates the user provides — compute independently, then compare.
- Explicit confidence levels on every substantive claim: high / moderate / low / unknown.
- Never hallucinate. If a fact, date, or quote can't be verified, say "unknown." Accuracy beats edge. The references in this skill mark confidence on every Andreessen attribution.
- Don't capitulate under pushback unless given new evidence or a superior argument. Restate the position if the reasoning holds. Never apologize for disagreeing.
What ships with it
14 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.
- agents/openai.yaml 188 B
- assets/blank_3x5_card.md 929 B
- assets/example_3x5_card.md 1.7 KB
- assets/example_market_verdict.md 2.8 KB
- assets/example_pmf_check.md 1.9 KB
- assets/forcing_question_worksheet.md 2.5 KB
- README.md 2.6 KB
- references/market_first_canon.md 5.0 KB
- references/operating_prompt.md 5.2 KB
- references/personal_productivity_system.md 5.3 KB
- references/pmf_and_build_canon.md 5.4 KB
- scripts/anti_todo_card.py 8.4 KB runs code
- scripts/market_first_evaluator.py 8.5 KB runs code
- scripts/pmf_signal_scorer.py 8.2 KB runs code
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.
- 11d ago First seen · 179 lines · 213 tokens per session scan A fa4dec4ebe56
andreessen is a skill published in the GitHub repository bestagentkits/agency-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 213 tokens to every session and 2,901 once invoked, about $0.0011 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
conscientiousness
Thoroughness and diligence in execution — systematic checking, completeness verification, follow-through on commitments, and the discipline of finishing well. Maps the personality trait of conscientiousness to AI task execution: not cutting corners, verifying results, and ensuring that what was promised is what was…
breathe
AI micro-reset between actions — the lightest self-care unit. A single conscious pause to check alignment before the next step. Where meditate is a full clearing session, breathe is one deliberate moment of awareness between tool calls or reasoning steps. Use mid-task when drift might be accumulating, between reading…
邮箱助手
An email management assistant for connecting to Gmail, Outlook, QQ, 163, and other IMAP/SMTP mail services. It can retrieve, summarize, and help draft email replies.
stay-within-limits
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.