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 agentmods add skills/impactbrussels/founderos/pivot-decisionnpx skills add impactbrussels/FounderOS --skill pivot-decisiongit clone --depth 1 https://github.com/impactbrussels/FounderOSWrote 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/impactbrussels/founderos/pivot-decision)<a href="https://agentmods.dev/skills/impactbrussels/founderos/pivot-decision"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/pivot-decision.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 | $0.00164 | $0.01340 |
| Opus 5 | $0.00082 | $0.00670 |
| Sonnet 5 | $0.00033 | $0.00268 |
| Haiku 4.5 | $0.00016 | $0.00134 |
Grade A, and why
pivot-decision 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make the Pivot Call
The hardest founder decision is not what to build, it is whether to keep going. Sunk cost, hope, and a few flattering data points keep dead ideas alive for months past the evidence, and they keep working ideas getting abandoned over one bad week. This skill turns "I'm not sure this is working" into a defensible persevere, pivot, or kill, grounded in what you actually measured, not what you wish were true.
The method
Built on the Founder OS scaffold (High tier). Full frameworks in references/pivot-playbook.md. This skill covers the whole persevere/pivot/kill call on one shared evidence base.
Step 1 - Lay out the evidence, cold
Before any decision, gather the real signals and separate what people did from what they said. Stated enthusiasm is not evidence; behaviour is.
| Signal | What it actually shows | Strong / weak / missing |
|---|---|---|
| Retention / repeat use | Whether the value is real and recurring | |
| Pipeline / conversion | Whether buyers move, not just nod | |
| Revenue / pre-payment | Whether anyone pays, not just praises | |
| Runway | How many more swings you have |
Step 2 - Score against the bar you set before you were attached
You committed to pass/fail bars in validate-idea and north-star-metrics. Hold the evidence
against those, not a goalpost you just moved. The question is never "could this work" (anything
could), it is "is it working, on the bar I set before I had feelings about it."
Step 3 - Name the call, and which kind of pivot
Decide persevere, pivot, or kill. If pivot, name which one the evidence supports (Eric Ries's taxonomy), because "pivot" without a type is just "try something else."
| The failing signal | The pivot it points to |
|---|---|
| Right problem, wrong slice of users | Customer-segment pivot |
| They want one feature, not the whole thing | Zoom-in pivot |
| Your thing is a feature of a bigger need | Zoom-out pivot |
| Real problem, wrong solution shape | Problem/solution pivot |
| Value lands, but you cannot reach them affordably | Channel pivot |
What ships with it
1 file 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 · 97 lines · 164 tokens per session scan A 93cbb193fb6d
pivot-decision is a skill published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 164 tokens to every session and 1,340 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
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.