mithra-mcp: Skill for Claude Code

.claude/skills/founder-board/SKILL.md

founder-board is a skill for Claude Code from RuiciroRS/mithra-mcp. It costs 94 tokens per session (1,413 once invoked), scanned A, original, MIT.

A structured business review in which three viewpoints examine an offer, its ability to stand out in a market, and the product experience. The viewpoints debate a specific product or growth question and produce a joint decision.

In plain words
What is it for?
Use it to assess pricing and buyer appeal, market defensibility, product focus, or a concrete growth decision.
Why use it?
It gives a repeatable way to challenge a business idea instead of relying on one opinion. Cross-questioning, scoring, and risk limits make disagreements and weak assumptions visible.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is RuiciroRS/mithra-mcp's own configuration. It tells Claude Code how to work on mithra-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mithra-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RuiciroRS/mithra-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/RuiciroRS/mithra-mcp/main/.claude/skills/founder-board/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/RuiciroRS/mithra-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for founder-board

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruicirors/mithra-mcp/founder-board/github.svg)](https://agentmods.dev/skills/ruicirors/mithra-mcp/founder-board)
Your own site
<a href="https://agentmods.dev/skills/ruicirors/mithra-mcp/founder-board"><img src="https://agentmods.dev/badge/skills/ruicirors/mithra-mcp/founder-board/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.

agentmods 80×15 button for founder-board

Your own site · 80×15
<a href="https://agentmods.dev/skills/ruicirors/mithra-mcp/founder-board"><img src="https://agentmods.dev/badge/skills/ruicirors/mithra-mcp/founder-board.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01413
Opus 5.5 $0.00038 $0.00565
Sonnet 5.5 $0.00019 $0.00283
Haiku 4.5 $0.00009 $0.00141

Measured 4d ago against content hash 07f0227717aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

founder-board 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.

.claude/skills/founder-board/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Founder Board

A board of three lenses. Each lens is a published business framework applied as a checklist — never a person, never an impersonation, never a voice. You (the main agent) are the Chair: you frame the question, run the rounds, enforce the rules and write the verdict. The lenses argue; the Chair does not vote.

Lens Asks Framework (summarised in our own words)
Offers Would the target buyer say yes at this price, today? The value-equation approach to offers: dream outcome × perceived likelihood, divided by time delay × effort; stacking, guarantees, pricing to value.
Monopoly Can this become the only answer for some market, and stay that way? The monopoly-vs-competition approach to startups: start with a small market and dominate it; proprietary technology (~10× better), network effects, economies of scale, brand; durability; distribution.
Product Is the experience focused, simple and complete enough to be loved by one specific person? The focus-and-simplicity approach to product: say no to almost everything, own the end-to-end experience, simplicity as the result of depth, taste in the details.

Full rubrics: references/lenses.md.

Hard rules

  1. Lenses are frameworks, not people. No first person as an author, no "as X would say", no catchphrases, no invented quotes. A lens speaks as "the Offers lens".
  2. No fabricated facts. If a number is unknown, the lens says so and names the cheapest way to find it out. Assumptions are labelled ASSUMPTION.
  3. Private by default. The verdict file stays in the user's project; nothing is sent anywhere. Do not ask for more data than the question needs.
  4. The Chair does not vote and never edits a lens's scores. It may only apply the caps in references/scoring.md.

Modes

  • Evaluate — "evaluate my product / idea". The single option is the product as described; each lens scores it 0–10 and votes FUND / FUND IF … / PASS.
  • Decide — "should we do A, B or C?". 2–4 options (the Chair adds "do nothing / keep current course" as a baseline if the user didn't). Each lens scores every option 0–10.

Read the full file on GitHub · 99 lines

Files

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.

Changes

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.

  1. 4d ago First seen · 99 lines · 94 tokens per session scan A 07f0227717aa

Subscribe to this mod's changes

founder-board is a skill published in the GitHub repository RuiciroRS/mithra-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 94 tokens to every session and 1,413 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-14.

Related

founder-board compared with skills from other repositories

founder-board next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
founder-boardRuiciroRS/mithra-mcpSkill04d agoMITA94Claude Code
web-accessopen-octo/octo-agentSkill151todayMITA139Claude Code, Codex
skill-creatoropen-octo/octo-agentSkill151todayMITA123Claude Code, Codex
save-learningcaliber-ai-org/ai-setupSkill1.3k1mo agoMITA71Claude Code, Codex
support-triagejin-bo/agentaoSkill313yesterdayMITA23Claude Code, Codex
repothewaltero/mythos-routerSkill3086d agoMITA11Claude Code, Codex
statusPerpetualSoftware/padSkill207todayApache-2.0A13Claude Code