agentmods.dev

exit-or-double-down

exit-or-double-down is a skill for Claude Code from daddia/claude-for-strategy. It costs 61 tokens per session (764 once invoked), scanned A, original, MIT.

A decision framework for choosing whether to exit a business unit, keep it, or invest more in it.

In plain words
What is it for?
Use it for portfolio reviews and explicit exit, hold, or double-down decisions when assessing a business unit's strategy and funding.
Why use it?
It separates future prospects from money already spent, known as sunk costs, and requires evidence, approval ownership, and criteria for ending or increasing investment.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the corporate-strategy plugin — 6 skills, 1 agent shipped together

not rated 2repo 2mo ago A scan 61 tokens original MIT

Good fit Use it for portfolio reviews and explicit exit, hold, or double-down decisions when assessing a business unit's strategy and funding.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/daddia/claude-for-strategy/exit-or-double-down
View source ↗ daddia/claude-for-strategy
Install

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.

Any agent
npx skills add daddia/claude-for-strategy --skill exit-or-double-down
Clone the repo
git clone --depth 1 https://github.com/daddia/claude-for-strategy

Made for: Claude Code.

Or install corporate-strategy, the plugin that ships this one along with the rest of its 6 skills, 1 agent.

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 exit-or-double-down

README.md
[![agentmods](https://agentmods.dev/badge/skills/daddia/claude-for-strategy/exit-or-double-down/github.svg)](https://agentmods.dev/skills/daddia/claude-for-strategy/exit-or-double-down)
Your own site
<a href="https://agentmods.dev/skills/daddia/claude-for-strategy/exit-or-double-down"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/exit-or-double-down/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 exit-or-double-down

Your own site · 80×15
<a href="https://agentmods.dev/skills/daddia/claude-for-strategy/exit-or-double-down"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/exit-or-double-down.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 764 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 $0.00061 $0.00764
Opus 5 $0.00030 $0.00382
Sonnet 5 $0.00012 $0.00153
Haiku 4.5 $0.00006 $0.00076

Measured 12d ago against content hash 497bd3382288, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

exit-or-double-down 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 12d 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.

corporate-strategy/skills/exit-or-double-down/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Exit or Double Down

When to use

Portfolio pruning — explicit exit/hold/double-down with blank-page test first and sunk-cost reasoning named when it appears.

What this skill does not do

  • Does not treat sunk cost as forward evidence — quoted and set aside.
  • Does not default to HOLD — requires justification + kill criteria.
  • Does not invent financials — INPUT NEEDED.
  • Does not name vague approver — routing per profile.

Preconditions

Input If missing
Org + corporate-strategy profiles practice-setup or [PROVISIONAL]
Unit scope and decision forum Ask

Provisional mode

Generic exit criteria; [PROVISIONAL] on thresholds.

Trust spine

  • Strategic advice vs. support (mandatory): CALL is recommendation; named forum approves.
  • Per trust-conventions; GATE before board/IC finals.

Workflow

  1. Orient — unit, forum, evidence, time pressure.
  2. Blank-page test first — enter today at this investment?
  3. Sunk-cost detection — quote patterns, set aside.
  4. Exit criteria check — structural decline, capital destruction, growth odds.
  5. Double-down criteria — position, leadership path, under-resourcing.
  6. CALL: EXIT | HOLD | DOUBLE DOWN — forward rationale only.
  7. Kill criteria if HOLD.
  8. Approval routing per profile.
  9. GATE if board-ready.

Output format

CONFIDENCE: [...]
UNIT: [...]
BLANK-PAGE TEST: [...]
SUNK-COST CHECK: [...]
EXIT CRITERIA: [table]
DOUBLE-DOWN CRITERIA: [table]
CALL: [...]
KILL CRITERIA (if HOLD): [...]
APPROVAL ROUTING: [...]

Worked example

Input: Legacy print unit, "we've spent $200M already" cited.

Excerpt: Blank-page: no. Sunk-cost quoted and set aside. EXIT criteria met on structural decline; CALL EXIT [review].

Quality checks before delivering

  • Blank-page before other evidence
  • Sunk cost named if present
  • Hold justified with kill criteria
  • Approver named

Propose profile update

When a stable convention surfaces during this run (thresholds, naming, tone, output format, or recurring corrections), propose a profile update: show the exact diff against ~/.claude/plugins/config/claude-for-strategy/corporate-strategy/CLAUDE.md (org-wide facts go to org-profile.md), ask for confirmation, and write only on yes. Only /corporate-strategy:practice-setup auto-applies a full profile write.

Read the full file on GitHub · 93 lines

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. 12d ago First seen · 93 lines · 61 tokens per session scan A 497bd3382288

Subscribe to this mod's changes

exit-or-double-down is a skill published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 764 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.

ConnectorsFinance and fintechPlanningagentsclaudecursormcpskills
Related

Other skills, from other repositories

defi-protocol-templates

Implement DeFi protocols with production-ready templates for staking, AMMs, governance, and flash loans. Use when building decentralized finance applications or smart contract protocols.

wshobson/agents · 38 tokens

prompt-proximity-architecture

Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…

elvisun/newsjack · 67 tokens

sera

Multi-currency settlement skill — quote, swap, and settle across 40 stablecoins via Sera Protocol.

sera-cx/sera-agents · 24 tokens

sera

Multi-currency settlement for AI agents. Quote, swap, and settle across 40 stablecoins (USDC, USDT, EURC, XSGD, JPYC, MYRT, TGBP, BRZ, MXNT, IDRT, AUDD, and more) and 22 fiat currencies via Sera Protocol. 55 tools — quotes, swaps, treasury management, FX deal scanning, and a maker spread ladder.

sera-cx/sera-agents · 90 tokens

swarmclaw

AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.

swarmclawai/swarmclaw · 67 tokens

x402

HTTP 402 payment protocol for AI agent commerce — three-actor model (Client, Resource Server, Facilitator), ERC-3009 transferWithAuthorization, server middleware (@x402/express), client patterns in TypeScript and Python, facilitator integration, agent-to-agent payments, pricing strategies, and replay protection. Works…

aomi-labs/skills · 84 tokens