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 abhisekjha/pith --skill pith-uninstallgit clone --depth 1 https://github.com/abhisekjha/pithWrote 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/abhisekjha/pith/pith-uninstall)<a href="https://agentmods.dev/skills/abhisekjha/pith/pith-uninstall"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-uninstall/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/abhisekjha/pith/pith-uninstall"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-uninstall.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 | $0.00048 | $0.00647 |
| Opus 5 | $0.00024 | $0.00324 |
| Sonnet 5 | $0.00010 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade D, and why
pith-uninstall scanned grade D with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
• pith entries in ~/.claude/settings.json Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.pith How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
- User runs
/pith uninstall - User asks "remove pith", "uninstall pith", or "clean up pith"
Steps
1 — Confirm intent
Before running, ask once:
This will remove:
• ~/.claude/hooks/pith/ (all hook scripts)
• ~/.claude/commands/pith.md, budget.md, focus.md
• pith entries in ~/.claude/settings.json
Your project wikis (wiki/) and token history (~/.pith/) are NOT deleted.
Proceed? (yes / no)
If user says no, stop. If yes, continue.
2 — Run the uninstall script
Locate the pith directory (same logic as pith-install step 1), then:
bash "<pith_dir>/uninstall.sh"
Stream the output so user sees each item removed.
3 — Verify clean
# Hooks gone
ls ~/.claude/hooks/pith/ 2>/dev/null && echo "STILL EXISTS" || echo "removed ok"
# Slash commands gone
ls ~/.claude/commands/ | grep -E "pith|budget|focus" 2>/dev/null && echo "STILL EXISTS" || echo "removed ok"
# Settings clean
node -e "const s=require(require('os').homedir()+'/.claude/settings.json'); const h=JSON.stringify(s.hooks||''); console.log(h.includes('pith')?'pith still in hooks':'hooks clean'); console.log(s.statusLine?'statusLine still set':'statusLine clean')"
4 — Optionally wipe all data
If the user said "remove everything" or "wipe all data", also run:
rm -rf ~/.pith
rm -f ~/.config/pith/config.json
Warn first: "This deletes your lifetime token savings history. Are you sure?"
5 — Confirm to user
Pith uninstalled.
Removed:
✓ hooks (session-start, post-tool-use, prompt-submit, stop)
✓ slash commands (/pith, /budget, /focus)
✓ settings.json entries
Preserved:
• wiki/ directories in your projects
• ~/.pith/state.json (token history)
To reinstall: /pith install
Error handling
| Error | Fix |
|---|---|
uninstall.sh not found |
Run the node cleanup inline: remove ~/.claude/hooks/pith, delete command files, patch settings manually |
settings.json malformed |
Show the file, offer to remove pith keys manually |
| Hook files already missing | Skip silently, still clean settings.json |
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 · 97 lines · 48 tokens per session scan D 81168c24a81a
pith-uninstall is a skill published in the GitHub repository abhisekjha/pith (98 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 647 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
test-run
Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.