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 skills add rfxlamia/pocketto --skill pocket-grindinggit 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-grinding)<a href="https://agentmods.dev/skills/rfxlamia/pocketto/pocket-grinding"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/pocket-grinding/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-grinding"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/pocket-grinding.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 | $0.00065 | $0.05490 |
| Opus 5 | $0.00032 | $0.02745 |
| Sonnet 5 | $0.00013 | $0.01098 |
| Haiku 4.5 | $0.00006 | $0.00549 |
Grade A, and why
pocket-grinding 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.
How it starts
The opening of the file, as written. The whole thing — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pocket Grinding
Production-grade requirement discovery using BDD principles. Gathers project context, defines scope, questions from three expert lenses, maps concrete examples to scenarios, validates against existing architecture, and produces a spec ready for delegation.
Core principle: Scenarios first, design second. Architecture must be validated before handoff. No implementation until spec is approved.
When to Use
Trigger this skill when:
- Planning a feature whose shape or requirements aren't yet clear, or that spans multiple files/phases (small, clearly-specified additions →
hotfix) - Fixing a non-trivial bug with design implications
- Refactoring a system boundary or changing an API contract
- User says "let's think through", "plan this", "explore options", "before we build"
Do NOT use for:
- Trivial single-line fixes (typo, config value, rename)
- Small, well-understood changes touching only 1–4 files and resolvable in 1–2 requests → use
hotfixinstead (Phase 1.5 surfaces this off-ramp mid-flow) - Work that already has an approved spec
Hard Gates
GATE 1: NO IMPLEMENTATION until Phase 7 handoff is complete and user approves.
No code, no scaffolding, no migrations — regardless of perceived simplicity.
GATE 2: NO PHASE 3 without confirmed scope.
Phase 2 must be user-confirmed before questioning starts.
Unconfirmed scope = wasted questions.
GATE 3: NO HANDOFF if architecture validation fails (Phase 6).
Loop back to Phase 5, revise design, re-validate.
GATE 4: POCKET-PLANNING MUST BE INVOKED after user approves spec.
Pocket-grinding is not done until pocket-planning receives the spec.
Do not stop at "spec written" — invoke pocket-planning immediately.
GATE 5: EDGE CASE HUNTER MUST RUN before Phase 5 and before handoff.
After GWT scenarios (Phase 4), dispatch the read-only edge case hunter
subagent — this is mandatory, not optional. Do NOT offer handoff to
pocket-planning until the hunter has run and its blocking findings are
resolved. If you catch yourself moving toward handoff without an edge
case hunter result, STOP and dispatch it first.
What ships with it
4 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.
- 10d ago First seen · 533 lines · 65 tokens per session scan A f6b509bb4295
pocket-grinding is a skill published in the GitHub repository rfxlamia/pocketto (5 stars, last pushed 18d ago), licensed MIT. It adds 65 tokens to every session and 5,490 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…
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.
techdebt
Analyze Elixir/Phoenix technical debt — duplicates, refactoring opportunities, credo issues. Use when asked about code quality, cleanup, or what to improve.
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.