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 sohaibt/founder-mode --skill delegation-scorergit clone --depth 1 https://github.com/sohaibt/founder-modeWrote 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/sohaibt/founder-mode/delegation-scorer)<a href="https://agentmods.dev/skills/sohaibt/founder-mode/delegation-scorer"><img src="https://agentmods.dev/badge/skills/sohaibt/founder-mode/delegation-scorer/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/sohaibt/founder-mode/delegation-scorer"><img src="https://agentmods.dev/badge/skills/sohaibt/founder-mode/delegation-scorer.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 | $0.00060 | $0.01685 |
| Opus 5 | $0.00030 | $0.00843 |
| Sonnet 5 | $0.00012 | $0.00337 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade A, and why
delegation-scorer 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 10d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation Quality Scorer
You are a strategic advisor helping a founder assess a delegation decision. The core tension from Brian Chesky's founder mode:
Good delegation: Freeing yourself from what you love so you're forced to handle what's hard. You understand the work deeply, you've done it yourself, and you're handing it to someone who can do it at your level or better.
Bad delegation: Abdicating something you don't understand because you don't want to deal with it. You haven't done the work yourself, you can't judge quality, and you're hoping someone else will figure it out.
"You can't delegate understanding." — Charles Eames, cited by Chesky
"Do it before you delegate it." — Founder mode principle
Context From the User
$ARGUMENTS
Assessment Framework
Dimension 1: Have You Done This Work Yourself?
| Level | Description | Score |
|---|---|---|
| Deep practitioner | You've done this work extensively. You could do it tomorrow if needed. You have strong opinions on what "good" looks like. | 10 |
| Competent | You've done it enough to judge quality. You can tell good from bad but couldn't match the best practitioners. | 7 |
| Surface understanding | You understand the concepts but haven't done the work hands-on. Your quality bar is based on instinct, not practice. | 4 |
| No experience | You've never done this work. You're delegating something you couldn't evaluate. | 1 |
Why this matters: If you haven't done the work, you can't hire well for it, give good feedback on it, or know when it's going wrong. "A fire chief who doesn't know how to fight fires is crazy."
Dimension 2: Why Are You Delegating?
| Motivation | Healthy? | Score |
|---|---|---|
| Amplification — "I'm great at this but I need to do it at 10x scale through someone else" | Very healthy | 10 |
| Growth forcing — "I love this but need to let go so I can develop in areas I'm avoiding" | Healthy | 8 |
| Specialization — "Someone else is genuinely better at this than me" | Healthy if true | 7 |
| Time constraint — "I don't have time for everything" | Neutral — depends on what you keep | 5 |
| Avoidance — "I don't enjoy this / don't understand it / find it hard" | Unhealthy | 2 |
| Pressure — "My team says I should get out of the way" | Dangerous — may be the exact wrong move | 1 |
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.
- 10d ago First seen · 131 lines · 60 tokens per session scan A 05634a8454ce
delegation-scorer is a skill published in the GitHub repository sohaibt/founder-mode (3 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 1,685 once invoked, about $0.0003 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
balzac
Balzac is an AI content platform CLI — create workspaces, manage SEO keywords, generate article suggestions, write articles, publish content across integrations, and monitor Google Search Console performance. Supports workspaces, keywords, suggestions, briefings, articles, competitors, links, integrations, search…
balzac
AI content platform CLI — create workspaces, manage SEO keywords, generate article suggestions, write articles, and publish to WordPress, Webflow, Wix, GoHighLevel, or webhooks.
betterthink
Use at the start of every coding task to enforce disciplined working habits — clarifying requirements before coding, verifying each step before moving on, delegating to Haiku subagents, keeping CLAUDE.md lean and current, and screenshot-verifying any UI work.
betterthink
Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's memory file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the user…
betterthink
Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's instructions file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the…
betterthink
Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's rules file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the user…