pickle-mode

pickle-mode is a skill for Claude Code from technicalpickles/pickled-claude-plugins. It costs 57 tokens per session (1,784 once invoked), scanned A, original, MIT.

A set of instructions for an AI coding assistant when a task spans multiple files, involves design choices, has an unclear bug, or needs performance work. It adds personal checks and procedures on top of another workflow called poteto-mode.

In plain words
What is it for?
Use it to guide multi-file changes, investigate bugs with unknown causes, make design decisions, and work on performance issues.
Why use it?
It gives the assistant a defined process for complex or uncertain changes instead of treating them like simple edits. It also tells the assistant which project rules take priority.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Part of the pickle-mode plugin — 1 skill shipped together

Good fit Use it to guide multi-file changes, investigate bugs with unknown causes, make design decisions, and work on performance issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/technicalpickles/pickled-claude-plugins/pickle-mode
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 technicalpickles/pickled-claude-plugins --skill pickle-mode
Clone the repo
git clone --depth 1 https://github.com/technicalpickles/pickled-claude-plugins

Made for: Claude Code.

Or install pickle-mode, the plugin that ships this one along with the rest of its 1 skill.

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 pickle-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/pickle-mode/github.svg)](https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/pickle-mode)
Your own site
<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/pickle-mode"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/pickle-mode/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 pickle-mode

Your own site · 80×15
<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/pickle-mode"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/pickle-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,784 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 $0.00057 $0.01784
Opus 5.5 $0.00023 $0.00714
Sonnet 5.5 $0.00011 $0.00357
Haiku 4.5 $0.00006 $0.00178

Measured today against content hash b5e0d4767280, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pickle-mode 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 today.

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.

plugins/pickle-mode/skills/pickle-mode/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pickle mode

A thin layer over pstack's poteto-mode. poteto-mode owns its principles, triggers, autonomy, subagent rules, reply rules, and playbook catalog. This file adds how the user thinks about work, plus the few places they work differently. Do not restate poteto-mode here.

Requirements

Invoke pstack:poteto-mode through the Skill tool before anything else. If it is not installed, stop and tell the user to install pstack@pstack-claude (https://github.com/michael-denyer/pstack-claude).

Precedence

On conflict, the first match wins:

  1. The user's own instructions (their messages, user-level CLAUDE.md).
  2. The instructions of the repository you are working in (its CLAUDE.md or AGENTS.md, and its .agents/playbooks/ overlays). When a task touches several repositories, each one's instructions govern the changes made in it.
  3. The pickle-mode principles, gates, and overlays below.
  4. poteto-mode.

Repository standards outrank pickle-mode on purpose. Git workflow, commit style, and review process belong to the repo.

Principles

How the user thinks about work. Apply these inside every playbook step, next to poteto-mode's principles. They are judgment, not procedure: they say what to weigh, not which command to run.

  • Understand why before doing what. When the user proposes an approach, learn what they are trying to accomplish first. Raise a better path early, before work starts. Once work is underway, never quietly swap in a different approach. Stop and raise it instead.
  • Look for what already exists. Before designing something, look for the skill, script, tool, or doc that already does it or most of it, and extend that before building new. Answer "don't we already have X?" before the user has to ask it.
  • Fix it, don't remove it. A bug, edge case, or review comment against a feature gets fixed in place. Deleting or disabling the feature to make the complaint go away is a decision for the user, not a fix. A deferral counts only once its follow-up exists.
  • Know what you're throwing away. Before deleting, cleaning up, or overwriting, find out what it is, where it came from, whether anything still uses it, and what it costs to rebuild, and write that down. What is still there matters more than tidiness.
  • Write for the reader who wasn't there. Docs, handoffs, and notes get read later by someone without this conversation. Use absolute dates and identifiers, correct a wrong claim in place instead of stacking a correction on it, and say what something is rather than what it isn't.
  • Reaching other people is a deliberate act. A message, tag, review request, or ping to someone else is a choice made on purpose, never a side effect of finishing a task. The Posting gate covers the mechanics.
  • A personal workshop, not a product. The user's own tooling serves one person's way of working. Optimize for how they work, not for a hypothetical adopter. Skip generality, onboarding, and configurability nobody asked for.

Read the full file on GitHub · 96 lines

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. today Changed · +19 lines · +3 tokens per session b5e0d4767280
  2. 6d ago First seen · 77 lines · 54 tokens per session scan A a24f1e2a9d6c

Subscribe to this mod's changes

pickle-mode is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (12 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,784 once invoked, about $0.0002 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 2026-11-04.

Related

pickle-mode compared with skills from other repositories

pickle-mode next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pickle-modetechnicalpickles/pickled-claude-pluginsSkill12todayMITA57Claude Code
create-agent-dotnetdiagrid-labs/dapr-skillsSkill134d agoMITA58Claude Code
create-pubsub-dotnetdiagrid-labs/dapr-skillsSkill134d agoMITA79Claude Code
create-pubsub-pythondiagrid-labs/dapr-skillsSkill134d agoMITA70Claude Code
create-workflow-from-diagramdiagrid-labs/dapr-skillsSkill134d agoMITA97Claude Code
create-workflow-typescriptdiagrid-labs/dapr-skillsSkill134d agoMITA69Claude Code
create-workflow-dotnetdiagrid-labs/dapr-skillsSkill134d agoMITA52Claude Code