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-installgit 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-install)<a href="https://agentmods.dev/skills/abhisekjha/pith/pith-install"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-install.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 | $0.00621 |
| Opus 5 | $0.00021 | $0.00311 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade B, and why
pith-install 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.
node -e "const s=require(require('os').homedir()+'/.claude/settings.json'); console.log(JSON.stringify({hooks:Object.keys(s.hooks||{}), statusLine:!!s.statusLine},null,2))" How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
- User runs
/pith install - User asks "how do I install pith" or "set up pith"
Steps
1 — Locate the pith directory
Find where pith lives. Try in order:
~/.claude/plugins/cache/pith/pith/*/(installed via plugin marketplace)- The directory containing this SKILL.md file (cloned from GitHub)
- Ask the user: "Where did you clone pith to?"
2 — Run the install script
bash "<pith_dir>/install.sh"
Stream the output to the user so they can see each step tick off.
3 — Verify success
After the script completes, confirm all five things installed:
# Hooks copied
ls ~/.claude/hooks/pith/
# Slash commands registered
ls ~/.claude/commands/ | grep -E "pith|budget|focus"
# Settings patched
node -e "const s=require(require('os').homedir()+'/.claude/settings.json'); console.log(JSON.stringify({hooks:Object.keys(s.hooks||{}), statusLine:!!s.statusLine},null,2))"
# Plugin root recorded
cat ~/.config/pith/config.json
# State dir exists
ls ~/.pith/
If any check fails, show the specific error and offer to re-run just that step.
4 — Confirm to user
Show this summary:
Pith installed.
Active automatically (zero config):
✓ Tool output compression
✓ Token meter in statusline [PITH 0k/200k]
✓ Auto-compact at 70% context
On-demand:
/pith lean|ultra|precise output compression
/pith debug|arch|plan structured formats
/pith commit commit message
/pith wiki project knowledge base
/pith status token usage
/pith tour interactive walkthrough
/budget <n> hard token ceiling
/focus <file> load relevant sections only
Restart Claude Code to activate hooks.
Error handling
| Error | Fix |
|---|---|
node: command not found |
Tell user to install Node.js ≥18 |
settings.json parse error |
Show the broken JSON, offer to reset to {} |
| Permission denied on hooks dir | Run mkdir -p ~/.claude/hooks/pith first |
| Plugin root not found | Ask user to re-clone: git clone https://github.com/abhisekjha/pith |
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 · 93 lines · 42 tokens per session scan B 9e7a10ce14bc
pith-install is a skill published in the GitHub repository abhisekjha/pith (98 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 621 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 2026-08-30.
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.