pocket-closing

pocket-closing is a skill for Claude Code from rfxlamia/pocketto. It costs 92 tokens per session (5,126 once invoked), scanned A, original, MIT.

A closing skill for finishing a Pocket development plan after its implementation and review results have been recorded.

In plain words
What is it for?
It is for reconciling review verdicts, moving approved work to done, running the closing step, and producing a closeout summary.
Why use it?
It prevents plans from being marked complete when reviews failed or were blocked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pocketto plugin — 13 skills shipped together

Good fit It is for reconciling review verdicts, moving approved work to done, running the closing step, and producing a closeout summary.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rfxlamia/pocketto/pocket-closing
Install

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.

Any agent
npx skills add rfxlamia/pocketto --skill pocket-closing
Clone the repo
git clone --depth 1 https://github.com/rfxlamia/pocketto

Made for: Claude Code.

Or install pocketto, the plugin that ships this one along with the rest of its 13 skills.

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.

agentmods badge for pocket-closing

README.md
[![agentmods](https://agentmods.dev/badge/skills/rfxlamia/pocketto/pocket-closing/github.svg)](https://agentmods.dev/skills/rfxlamia/pocketto/pocket-closing)
Your own site
<a href="https://agentmods.dev/skills/rfxlamia/pocketto/pocket-closing"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/pocket-closing/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.

agentmods 80×15 button for pocket-closing

Your own site · 80×15
<a href="https://agentmods.dev/skills/rfxlamia/pocketto/pocket-closing"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/pocket-closing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.05126
Opus 5 $0.00046 $0.02563
Sonnet 5 $0.00018 $0.01025
Haiku 4.5 $0.00009 $0.00513

Measured 10d ago against content hash 0fcddb9cd0b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pocket-closing 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 10d 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.

skills/pocket-closing/SKILL.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pocket Closing

The terminal stage of the Pocket pipeline. Invoked directly by the user after pocket-development's phase-level pass has written verdicts for a phase or flat plan. It reconciles those verdicts against the execution log, gates closure on review results, advances state, and produces the closeout artifact that ends the plan.

Core principle: Verdicts decide. pocket-closing never re-reviews and never improvises a close — it reads what pocket-development's phase-level pass wrote and translates it into an accept-and-close or a block. No clean verdict, no close.

Position in Pocket Bundle

pocket-grinding → pocket-planning → pocket-structuring → pocket-development → POCKET-CLOSING
                                                                                    ↑
                                                                  User invokes directly after
                                                                  pocket-development's phase-level pass
                                                                  reaches REVIEW on all tasks passing

pocket-closing is always invoked directly by the user (/pocketto:pocket-closing <path>) — pocket-development never auto-chains to it. When a phase passes with all REVIEW_PASS, the phase-level pass advances the phase to REVIEW and emits a PHASE_COMPLETE handoff naming pocket-closing as the next step; the user then runs it. pocket-closing owns the close from scratch: the phase-level pass deliberately does NOT update log.json ("leave to user or pocket-closing"), so this skill still runs its full preflight, verdict gate, freshness check, and log close. pocket-development names log.json as "pocket-closing's primary input." This skill is where the loop actually closes.

Invocation

/pocketto:pocket-closing <path-to-execution-plan-or-plan-dir>

Examples:

/pocketto:pocket-closing docs/pocket/plans/2026-06-03-typing-dna/
/pocketto:pocket-closing docs/pocket/plans/2026-05-28-auth/execution-plan/phase-2.md

Read the full file on GitHub · 410 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 410 lines · 92 tokens per session scan A 0fcddb9cd0b1

Subscribe to this mod's changes

pocket-closing is a skill published in the GitHub repository rfxlamia/pocketto (5 stars, last pushed 17d ago), licensed MIT. It adds 92 tokens to every session and 5,126 once invoked, about $0.0005 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.