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/capturenpx skills add msolecki/founder-os --skill capturegit 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/capture)<a href="https://agentmods.dev/skills/msolecki/founder-os/capture"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/capture.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 | $0.00031 | $0.00899 |
| Opus 5 | $0.00015 | $0.00449 |
| Sonnet 5 | $0.00006 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
capture 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture
This is the lowest-ceremony door into Founder OS: one founder-supplied line goes into the inbox, and no agent pretends to know what it means yet.
When to use
Use when the founder has one thought, obligation, or observation to retain but
does not want to stop and route it. Use triage when the input is already a
pile, and queue only after an obligation has actually been classified.
Inputs
Resolve exactly one business workspace. Read the full inbox.md through
read_state; do not read another business file to classify or enrich the line.
Accept one raw command argument. It must be one nonblank logical line of at most 2048 UTF-8 bytes. Whitespace-only input is blank. Reject NUL, newline, and carriage return characters before any write. Do not trim or normalize the accepted argument, and do not split rejected multiline input into several captures.
Beliefs
- Capture that asks for a priority is prioritization wearing an intake label; the moment belongs to remembering, not deciding.
- A timestamp added by the system is false precision: it records when the tool ran, not when the founder first knew the thought mattered.
- An inbox line that becomes a queue item before triage has silently allowed arrival order to decide the company.
Steps
- Validate the raw argument against the input contract before mutation. On
rejection, name the violated limit and stop without calling
write_owned_state. - Resolve the business. An ambiguous workspace stops with
WORKSPACE_UNRESOLVED; never guess another business and perform no read or write there. - Use
read_stateto read the fullinbox.mdand retain its observed SHA-256. Require its one declared## Inboxheading. - Build one proposed full document in memory. Preserve every existing byte and
append exactly one Markdown list item under
## Inbox: prefix-, then the founder's accepted bytes unchanged, then the document's line ending. The safe list prefix prevents input such as## Urgentfrom becoming a document heading. - Call
write_owned_statewith the active capability,inbox.md, the proposed full document, and the observed SHA-256 as the expected hash in the gateway'sexpected_sha256field; never omit it on an existing inbox. Apply the sharedSTALE_WRITErecovery at most once; every final failure stops without a success receipt. - After a successful write, re-read the full file. Verify the exact appended list item and that the earlier bytes remain intact. Only that re-read may produce the workflow result below.
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 · 89 lines · 31 tokens per session scan A 578535e009e9
capture is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 899 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…