Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add technicalpickles/pickled-claude-plugins/plugin install dev-toolsWrote 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/technicalpickles/pickled-claude-plugins/working-in-scratch-areas)<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/working-in-scratch-areas"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/working-in-scratch-areas.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 5.1 | $0.00042 | $0.04248 |
| Opus 5 | $0.00021 | $0.02124 |
| Sonnet 5 | $0.00008 | $0.00850 |
| Haiku 4.5 | $0.00004 | $0.00425 |
Grade B, and why
working-in-scratch-areas scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -i "scratch areas:" ~/.claude/CLAUDE.md How it starts
The opening of the file, as written. The whole thing — 628 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in Scratch Areas
Overview
Helps Claude save one-off scripts and documents to persistent scratch areas instead of littering repositories with temporary files or using /tmp.
Core principles:
- Temporary work deserves permanent storage
- Scripts and documents should be documented, organized, and preserved
- Never use
/tmpor projecttmp/directories for these files - Files belong in
.scratch/subdirectories with context
Announce at start: "I'm using the working-in-scratch-areas skill."
When to Use
Use this skill when creating:
- One-off debug scripts
- Analysis or investigation tools
- Temporary documentation or reports
- Quick test scripts
- Data extraction utilities
- Monitoring or diagnostic tools
Don't use for:
- Production code that belongs in the main codebase
- Configuration files that should be committed
- Tests that belong in the test suite
- Documentation that should be in docs/
NEVER use /tmp or project tmp/ directories. Always use .scratch/ for temporary work.
Setup Workflow
Check for Existing Scratch Area
First, check if a scratch area already exists:
test -L .scratch && echo "Scratch area exists" || echo "No scratch area"
If the symlink exists, verify gitignore is configured (see below), then you're ready to use it.
Setting Up New Scratch Area
When no scratch area exists:
- Detect: "I notice this repository doesn't have a scratch area set up."
- Check CLAUDE.md: Check if scratch areas location is configured in
~/.claude/CLAUDE.md - If not configured: Ask user where they want scratch areas with AskUserQuestion tool
- Run setup script with the chosen location
- Optionally save the location to CLAUDE.md for future use
Setup Steps:
# 1. Get repo root
git rev-parse --show-toplevel
# Output: /Users/josh/workspace/some-repo
# 2. Check if configured in CLAUDE.md
grep -i "scratch areas:" ~/.claude/CLAUDE.md
# 3a. If configured, run setup (reads from CLAUDE.md automatically)
cd /Users/josh/workspace/some-repo && ~/.claude/skills/working-in-scratch-areas/scripts/setup-scratch-area.sh
# 3b. If not configured, ask user for location and run with --areas-root
cd /Users/josh/workspace/some-repo && ~/.claude/skills/working-in-scratch-areas/scripts/setup-scratch-area.sh --areas-root ~/workspace/scratch-areas
# 3c. If user wants to save preference, add --save-to-claude-md flag
cd /Users/josh/workspace/some-repo && ~/.claude/skills/working-in-scratch-areas/scripts/setup-scratch-area.sh --areas-root ~/workspace/scratch-areas --save-to-claude-md
# 4. Verify gitignore (see Gitignore Setup section below)
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.
- 8d ago First seen · 628 lines · 42 tokens per session scan B 82f980673622
working-in-scratch-areas is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (10 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 4,248 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
project-memory
Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.
project-retrospective
Generate a LESSONS.md from a finished project: what worked, what didn't, what to reuse, what to retire — formatted for next-project carry-over.
template-selector
Recommend the right skill bundle, agent, and workflow sequence for a new project — so media professionals can start producing instead of browsing a 394-skill library.
absolute-simplify
Use when the user wants to simplify, clean up, refactor, tidy, or refine code — their staged/unstaged git changes or a target file/path. Reduces complexity, flattens nesting, removes redundancy and dead code, scores each change by value (holding low-value churn), then runs tests to prove nothing broke. Invoke on…
absolute-ui
Build polished, intentional UIs with concrete CSS/Tailwind values — typography, color, layout, spacing, dark mode, accessibility, animations, components. Encodes specific, opinionated rules with exact values, not vague advice. Covers buttons, cards, forms, tables, navigation, dashboards, landing pages, onboarding, and…
absolute-work
End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this…