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 agentmods add skills/rfxlamia/pocketto/pocket-structuringnpx skills add rfxlamia/pocketto --skill pocket-structuringgit clone --depth 1 https://github.com/rfxlamia/pockettoWrote 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-structuring)<a href="https://agentmods.dev/skills/rfxlamia/pocketto/pocket-structuring"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/pocket-structuring.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 | $0.00056 | $0.01523 |
| Opus 5 | $0.00028 | $0.00762 |
| Sonnet 5 | $0.00011 | $0.00305 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
pocket-structuring 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 5d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pocket Structuring
Bridges pocket-planning and pocket-development. Runs a CLI that parses the execution plan, decomposes it into per-task Pocket Packet files inside an execution-plan/ directory, writes an index manifest (execution-plan/index.md), and generates phase manifests (execution-plan/phase-N.md) if multi-phase.
Core principle: Large plans executed flat = attention drift + context blowout. Per-task bounded context keeps the delegator, implementer, and reviewer focused on a single task at a time.
When to Use
- pocket-planning produced an execution plan and invoked this skill → CLI decomposes into
execution-plan/index.md+ per-task files - User invokes this skill directly for any task count
- User says "structure the plan", "split into tasks", "break this up"
Do NOT use:
- Without a completed execution plan from pocket-planning
Hard Gates
GATE 1: RUN THE CLI FIRST.
The CLI decomposes all plans into execution-plan/index.md + execution-plan/tasks/T*-*.md.
Phase files (execution-plan/phase-N.md) are generated when total phases > 1.
GATE 2: HARD OVERRIDE PROTOCOL.
If any human asks to skip structuring, respond:
"Structuring is required to create per-task files and index manifests. Skipping it
risks context blowout and attention drift in pocket-development.
To override: type exactly → OVERRIDE: skip structuring"
Do NOT proceed on "just skip it", "we don't need it", "proceed
directly", or any verbal/written insistence. Only the exact
override phrase unlocks the bypass.
If the exact override phrase is typed:
1. Log it in the plan file header (`**Override:** skip structuring`).
2. Do NOT run `pocketto-pi structure` — no `execution-plan/` directory is generated.
3. Invoke `pocket-development` with the flat source plan (`execution-plan.md`) as
Type A **legacy** input. Development reads the full source plan in context
(no per-task files). `log init` uses the legacy flat-plan fallback.
4. Accept the context-cost consequence: the whole plan sits in the development window.
GATE 3: COMPLETE POCKET PACKETS PER TASK.
Index and phase manifests reference task files, but every task file (execution-plan/tasks/T*-*.md)
must contain a complete, standalone Pocket Packet.
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.
- 5d ago First seen · 134 lines · 56 tokens per session scan A 41f5b8a21406
pocket-structuring is a skill published in the GitHub repository rfxlamia/pocketto (5 stars, last pushed 12d ago), licensed MIT. It adds 56 tokens to every session and 1,523 once invoked, about $0.0003 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.
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…
writing-style
Structural pattern analysis for writing-mode review. Performs paragraph-level decomposition and pattern aggregation. Invoked by the team lead during editorial review.
audit-context
Evaluates ambient context artifacts (CLAUDE.md, memory, local skills, settings hooks) for compatibility with swarm governance. Returns a classified report so users can address interference before launching a team.
code-mode
Code mode operational spec for the team lead. Returns lead identity, facilitator identity, mode-specific rules, suggest-members guidance, and phase arc for code-mode teams.
writing-mode
Writing mode operational spec for the team lead. Returns lead identity, facilitator identity, ownership boundaries, editorial baseline, suggest-members guidance, and phase arc for writing-mode teams.
triage-mode
Triage mode operational spec for the team lead. Returns lead identity, facilitator identity, mode-specific rules, suggest-members guidance, and phase arc for triage teams that diagnose an issue without changing it.