Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
The line at the top of this page pins the label git:20260610.b440b26, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
B 13 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
fail: Size between 200 bytes and 200 KB (87 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Starting a new one? Use a template for AGENTS.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
GitHub
rfxlamia/pocketto · 6 stars · license MIT · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_asqjf3pnclc4nycd
GET https://markdownregistry.com/api/v1/resolve?ref=rfxlamia/pocketto/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/d2ad7cee837c835221a053464aa72975dde865c799bc1922a769f9de56f3ac46
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
rfxlamia/pocketto · skills/brand-design/SKILL.md · Brand-aware design system generator that acts as Head of Brand. Translates abstract brand language into a…
rfxlamia/pocketto · skills/bug-hunting/SKILL.md · Use when fixing bugs, debugging failures, or proactively reviewing code for hidden bugs. Reactive mode: fix known bugs…
rfxlamia/pocketto · skills/create-pr/SKILL.md · User-triggered Enterprise PR recorder for a completed phase. Stacked plans publish their phase branch through the…
rfxlamia/pocketto · skills/hotfix/SKILL.md · Fast iteration workflow with mandatory subagent plan review. Use when implementing small-to-medium changes quickly…
rfxlamia/pocketto · skills/pocket-closing/SKILL.md · Close a reviewed Pocket phase or plan when the user explicitly requests closeout, including as part of an end-to-end…
rfxlamia/pocketto · skills/pocket-education/SKILL.md · Pocket Education — mentor mode where the human writes the code and the agent teaches, reviews, and guides with…
rfxlamia/pocketto · skills/pocket-enterprise/SKILL.md · Adds the registered Enterprise lifecycle adapter to a compatible Core installation. Use only when the user explicitly…
rfxlamia/pocketto · skills/pocket-grinding/SKILL.md · BDD-driven feature/fix discovery before any implementation. Use when planning a feature, designing a fix, or exploring…
rfxlamia/pocketto · skills/pocket-help/SKILL.md · Onboarding and routing guide for the Pocket skill ecosystem. Use when someone asks what Pocket is, which skill to use…
rfxlamia/pocketto · skills/pocket-init/SKILL.md · Onboards an existing project onto Pocket by scanning its local configuration, writing a merge-safe project guide, and…
