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 skills add kothari-nikunj/nock --skill build-your-nockgit clone --depth 1 https://github.com/kothari-nikunj/nockWrote 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/kothari-nikunj/nock/build-your-nock)<a href="https://agentmods.dev/skills/kothari-nikunj/nock/build-your-nock"><img src="https://agentmods.dev/badge/skills/kothari-nikunj/nock/build-your-nock/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.
<a href="https://agentmods.dev/skills/kothari-nikunj/nock/build-your-nock"><img src="https://agentmods.dev/badge/skills/kothari-nikunj/nock/build-your-nock.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00131 | $0.03123 |
| Opus 5.5 | $0.00052 | $0.01249 |
| Sonnet 5.5 | $0.00026 | $0.00625 |
| Haiku 4.5 | $0.00013 | $0.00312 |
Grade A, and why
build-your-nock 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 2mo 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Your Nock
A playbook to turn an investor's own recorded pitch meetings into a reusable lens (a "Nock" of your own) that reviews any founder's deck the way they would — surfacing the questions they'd ask and the gaps they'd push on.
The output is a second skill (like nock) personalized to the investor: a question-bank.md
(their recurring questions, by theme) + a principles.md (the bar beneath the questions), plus the
logic to apply both to a deck.
The flow: pull → filter → extract → distill → calibrate against a few real decks → finalize. The calibration step (Stage A5) is what turns a plausible lens into one that actually sounds like the investor — it asks them to upload a handful of named decks and checks the lens's predictions against what they really asked in those meetings.
The architecture — and the one seam that matters
Two stages, separated by a privacy seam:
STAGE A — DISTILL (private, on your machine, uses raw transcripts)
your recorded pitch meetings ──► your "lens": question-bank.md + principles.md
↑ raw transcripts never leave this stage
STAGE B — APPLY (shareable: the anonymized lens only)
a founder's deck + your lens ──► questions you'd ask + what's missing
The distilled, anonymized lens is the only artifact safe to hand a founder. Raw transcripts and real company names stay local. Build with that seam in mind from step one.
Prerequisites
- Granola on a Business plan (gives API access). The normal case is one account, one workspace — this playbook assumes that. (If you happen to run multiple workspaces, mint one API key per workspace and run the pull once per key; otherwise ignore.)
- Your own writing on what you look for — essays, memos, investment-thesis docs, threads. Optional but it's what makes the lens sound like you rather than a generic VC. Have it ready to paste.
Stage A1 — Pull your meetings (Granola API)
Granola's official REST API. One key, one workspace.
What ships with it
3 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.
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.
- 2mo ago First seen · 196 lines · 131 tokens per session scan A 719dd0c7045d
build-your-nock is a skill published in the GitHub repository kothari-nikunj/nock (12 stars, last pushed 2mo ago), licensed MIT. It adds 131 tokens to every session and 3,123 once invoked, about $0.0005 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 2026-08-31.
build-your-nock compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| build-your-nockkothari-nikunj/nock | Skill | 12 | 2mo ago | MIT | A | 131 | Claude Code, Codex |
| fs-creative-voltagenexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 49 | Claude Code, Codex |
| ib-pitch-booknexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| html-ppt-zhangzara-bold-posternexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 47 | Claude Code, Codex |
| pitch-deckericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 116 | Claude Code, Codex |
| html-ppt-pitch-decknexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 50 | Claude Code, Codex |
| write-business-planjeffreytse/grimoire-core | Skill | 6 | 21d ago | MIT | A | 28 | Claude Code |