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/msolecki/founder-os/kill-or-continuenpx skills add msolecki/founder-os --skill kill-or-continuegit clone --depth 1 https://github.com/msolecki/founder-osWrote 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/msolecki/founder-os/kill-or-continue)<a href="https://agentmods.dev/skills/msolecki/founder-os/kill-or-continue"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/kill-or-continue.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 | $0.00033 | $0.02066 |
| Opus 5 | $0.00016 | $0.01033 |
| Sonnet 5 | $0.00007 | $0.00413 |
| Haiku 4.5 | $0.00003 | $0.00207 |
Grade A, and why
kill-or-continue 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 3d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kill or Continue
This is the job nobody hires for and every company of one needs. Ideas are not scarce; endings are. Nothing gets killed, so everything runs at 20%, and the founder concludes they need more discipline when what they need is fewer live bets.
There are two answers. "Let's give it another month" is not one of them.
When to use
The moment a bet's judgement date passes. Not a week after, when the answer has had time to soften.
Also when the Chief of Staff reports from weekly-review that a bet has had
zero days of attention for three consecutive weeks. That is a verdict the
founder has already reached with their calendar; this skill just makes them say
it.
Inputs
Read first — house rule 1:
goals.md— the bet, its threshold, its kill condition, its judgement datemetrics.md— the number that settles it, and the close datedecisions/— the entry where this bet was committed: what did they believe?reviews/quarterly/— has this bet already been extended once?
Shared sibling request
Every role transition returns one request to the main thread with exactly
role, workflow, workspace_id, correlation_id, handoff, and
expected_persistence. It carries one bounded handoff of at most 4096 UTF-8
bytes. The main thread passes the carried answer unchanged and executes the
request; this workflow never executes another role. Native and generic
execution use the byte-identical packaged role under
references/orchestration.md.
Beliefs
- Attention is a verdict, and it is issued weeks before anybody says it out loud. A bet with zero days of work behind it has already been killed by the calendar. Everything after that is paperwork the founder is declining to sign.
- Continuing has no invoice. Killing feels like the loss because it comes with a date and a number attached, while a bet running at 20% for another quarter costs more and never sends a bill. That asymmetry is why the default is continue, and why the default is usually wrong.
- Adjectives are the tell. "Promising", "basically working", "too early to tell" — a bet is ahead of the threshold it was given or it is not, and a founder reaching for a word instead of a number has already answered. "Too early to tell" is comfortable precisely because nothing can settle it.
- The founder is not attached to this bet. They are attached to being someone who finishes what they start — a good trait that is currently costing them a quarter. Say it plainly: this is not a character test, and the kill is not evidence about them.
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.
- 3d ago First seen · 173 lines · 33 tokens per session scan A 9dade5516893
kill-or-continue is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 2,066 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…