Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/vincentkoc/dotskills/graincrawl)<a href="https://agentmods.dev/skills/vincentkoc/dotskills/graincrawl"><img src="https://agentmods.dev/badge/skills/vincentkoc/dotskills/graincrawl.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 | $0.00047 | $0.00829 |
| Opus 5 | $0.00023 | $0.00415 |
| Sonnet 5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
graincrawl 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 6d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graincrawl
Purpose
Maintain graincrawl, the Go CLI that archives Granola notes, transcripts,
panels, people, workspaces, and sync metadata into a private local SQLite store.
Keep it read-only against Granola, SQLite-first for browsing/export, and aligned
with the other crawl apps.
When to use
- Editing or reviewing a
graincrawlcheckout. - Investigating Granola source adapters:
private-api,desktop-cache,encrypted-json,opfs,public-api, orcompanion-cli. - Verifying note, transcript, panel, source object, search, Markdown export, or TUI behavior.
- Preparing a
graincrawlrelease, Homebrew formula, or local binary refresh. - Checking crawlkit control metadata, snapshots, or TUI integration from the app side.
Workflow
-
Locate the
graincrawlcheckout from the current repository, an explicit user path, or the configured workspace root. Read repo-localAGENTS.md,README.md,SPEC.md, anddocs/security.mdbefore release, source-adapter, or unlock work. -
Keep Granola boundaries explicit. Ordinary
doctor,status,notes,export, andtuicommands must not prompt Keychain, unwrap safeStorage, or mutate Granola profile files. -
Use temp
HOME, temp XDG dirs, temp config, and temp SQLite databases for tests and smoke checks. Do not mutate live~/.config/graincrawlarchives or Granola app data unless the user explicitly asks. -
Prefer archived SQLite reads for UI/export behavior. If Markdown export has the data, TUI detail should read that same archived source, not re-query Granola.
-
Run the normal local gate with workspace masking disabled:
GOWORK=off go mod tidy git diff --exit-code -- go.mod go.sum GOWORK=off go vet ./... GOWORK=off go test -count=1 ./... make smoke goreleaser check -
For release work, use semver tags and verify the tap path:
git tag -a v0.1.0 -m "graincrawl v0.1.0" git push origin main v0.1.0 HOMEBREW_NO_AUTO_UPDATE=1 brew install --build-from-source vincentkoc/tap/graincrawl HOMEBREW_NO_AUTO_UPDATE=1 brew test vincentkoc/tap/graincrawl
What ships with it
2 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.
- 6d ago First seen · 87 lines · 47 tokens per session scan A 8eafaf97a1b8
graincrawl is a skill published in the GitHub repository vincentkoc/dotskills (102 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 829 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 2026-08-30.
Other skills, from other repositories
ship
Commit and push the current work properly — lint, run the release gate, write a detailed commit message, push to GitHub. Use whenever work reaches a milestone or the user says ship it, commit, or push.
development-delivery
通用开发生命周期的「交付、发布与部署」阶段 owner；当结果已经达到交付条件，或用户明确要求提交、发布、部署时使用，负责授权边界、结果交接和专项发布路由，不负责实现或 Review。.
nextclaw-npm-release
NextClaw NPM package 与 runtime channel 发布的专项流程 owner；用于发布 NPM、NPM 测试版、NextClaw 常规正式版及其恢复，覆盖 beta/stable、真实安装和分支回流，并按当前阶段读取一个 reference。.
nextclaw-desktop-release
NextClaw Desktop 构建、发布、恢复与运行冒烟流程 owner。.
pre-release-check
The final gate before a release is cut — go green, reconcile the release PR against what actually landed, sweep what CI can't see, check the roadmap and ADR statuses, optionally deep-review, then return a ship-or-hold verdict.
nextclaw-release-notes
当用户要求提交、收尾、changelog、release notes、版本更新笔记或发布变更汇总时使用；先选择提交范围判断、版本笔记、配图/社交一个阶段并读取对应 reference。.