Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rfxlamia/pockettonpx agentmods add skills/rfxlamia/pocketto/pocket-enterpriseWrote 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/rfxlamia/pocketto/pocket-enterprise)<a href="https://agentmods.dev/skills/rfxlamia/pocketto/pocket-enterprise"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/pocket-enterprise/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/rfxlamia/pocketto/pocket-enterprise"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/pocket-enterprise.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.01424 |
| Opus 5.5 | $0.00011 | $0.00570 |
| Sonnet 5.5 | $0.00006 | $0.00285 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
pocket-enterprise 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 yesterday.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pocket Enterprise
Pocket Enterprise is an optional, additive adapter for teams that explicitly choose remote lifecycle synchronization. Install the Enterprise role beside its matching Core role; it does not bundle or copy Core skills.
Core principle: Core commits local state and neutral lifecycle events first. Core does not call gh, does not merge pull requests, and does not close issues. The adapter validates compatibility before any external operation, reconciles events deterministically, and leaves ambiguous ownership for a human.
Release and compatibility
The surfaces.json manifest has schema 1 and defines exactly pi/core, pi/enterprise, claude/core, and claude/enterprise. Enterprise roles are deltas requiring their matching Core role. Release versions are package 4.2.2, CLI CONTRACT=3, PIPELINE=5, lifecycle schema 2, adapter contract 2, and surface manifest 1; these are independent version boundaries.
| Core | Enterprise | Result |
|---|---|---|
| v3 | v3 | Legacy installation remains operational with a v4 warning. |
| v4 | v4 | Supported. |
| v4 | absent | Core remains local-first; pending events are retained without GitHub calls. |
| v3 | v4 | Enterprise fails closed with Core upgrade guidance; v3 Core remains usable. |
| v4 | v3 | The adapter fails closed with Enterprise upgrade guidance; pending v4 events are retained. |
The v4 preflight warns about legacy v3 installations; an unchanged v3 binary cannot warn about a future release. Never infer consent from a remote or credentials. A registration must declare adapter contract 2; reinstall the adapter after upgrading, because a contract 1 registration fails preflight with ENTERPRISE_ADAPTER_CONTRACT_MISMATCH. Follow references/onboarding.md for setup, phase-branch options, and registration.
Activation and preflight
Run the Enterprise preflight from the project root:
node enterprise/cli.js preflight <project-root> --json
enterprise/cli.js is in the pocketto-pi package root, not in the project being checked. The command above is a checkout of this repository. A project that depends on the npm package runs node node_modules/pocketto-pi/enterprise/cli.js preflight <project-root> --json.
What ships with it
5 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.
- yesterday Changed 13b90a9fc204
- 3d ago Changed 100aa5d44e65
- 4d ago Changed 8c7163652f68
- 5d ago Changed · +1 lines 9cc9a89c96ba
- 7d ago Changed bc33d228393f
- 9d ago First seen · 79 lines · 28 tokens per session scan A 32785a1fbfa9
pocket-enterprise is a skill published in the GitHub repository rfxlamia/pocketto (5 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,424 once invoked, about $0.0001 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 2026-10-08.
Other skills, from other repositories
independent-review-loop
Independent review loop run before delivery in code work. An independent reviewer (Codex, or fresh Codex-style subagents) reads the whole PR against the approved outcome; the lead fixes in-scope functional findings and re-reviews until none remain. Its differentiator is independence and exhaustiveness — a reviewer…
resolve-dispute
Resolves stuck review findings via a put-up-or-concede exchange. Invoked by the facilitator when a finding survives arbitration without new evidence.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
triage
Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.
refactoring-patterns
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when…
techdebt
Analyze Elixir/Phoenix technical debt — duplicates, refactoring opportunities, credo issues. Use when asked about code quality, cleanup, or what to improve.