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 agentmods add skills/abhisekjha/pith/pith-setupnpx skills add abhisekjha/pith --skill pith-setupgit 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-setup)<a href="https://agentmods.dev/skills/abhisekjha/pith/pith-setup"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-setup.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 | $0.00044 | $0.00685 |
| Opus 5 | $0.00022 | $0.00342 |
| Sonnet 5 | $0.00009 | $0.00137 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
pith-setup 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 6d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding script for Claude
On the user's FIRST MESSAGE this session, respond with this exact introduction — then ask ONE question. Do not dump everything at once.
Introduction (2 sentences, then one question):
Pith is active — token compression running automatically. I can also build a project wiki that captures decisions, architecture, and learnings as we work — gets richer every session.
New project or existing codebase?
Greenfield flow (user says "new" or similar)
Ask these three questions, one at a time:
- "What does this project do? One sentence is fine."
- "Tech stack? Rough is fine."
- "Just you, or a team?"
After getting answers, run python3 ~/.local/share/pith/tools/setup.py --type greenfield with the answers as context, then say:
Wiki ready. I'll maintain it as we build — decisions, architecture, key entities. Every session it gets richer.
What are we building first?
Brownfield flow (user says "existing" or similar)
Ask these three questions, one at a time:
- "What does it do? One sentence."
- "What's the main pain — losing context between sessions, onboarding new people, documenting decisions?"
- "Want me to bootstrap the wiki from the existing code? I'll read the codebase and write initial pages. Takes one session."
If they want bootstrap:
Starting bootstrap. I'll read the main modules and write pages as I go — you'll see the wiki build in real time. Tell me if I'm missing something important.
Then run the bootstrap: explore src/, read main files (compressed by Pith automatically), write entity and concept pages, update index.md and log.md.
If they skip bootstrap:
No problem. I'll start building the wiki from today's work. Every decision and solution we reach, I'll offer to save it.
Run python3 ~/.local/share/pith/tools/setup.py --type brownfield and mark setup complete.
After setup (both flows)
Mark project as setup done: save setup_done: true in project state.
End onboarding with:
Commands:
/pith lean|precise|ultra— output compression/pith debug|review|arch|plan|commit— structured formats/pith wiki "<question>"— search the wiki/pith ingest <file>— add a source to the wiki/pith status— token usage this session/budget 150— hard token ceilingWhat are we working on?
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.
- 6d ago First seen · 83 lines · 44 tokens per session scan A 994a487d1ea4
pith-setup is a skill published in the GitHub repository abhisekjha/pith (98 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 685 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
s-continue
Cheaper and faster than /compact. Restores previous session context from Claude Code AND Codex transcripts by reading them directly — no LLM calls, no token cost. Also auto-loads a handoff written by /s-compact, if one exists. Triggers on "s-continue", "restore context", "what was I doing", "pick up where I left off"…
dt-usage
Use when the user adds, changes, removes, or announces a change to business behavior — a new endpoint, model, command, signal, event, validation rule, form, page, module, architectural decision, feature flag, supersedes relation, or dependency between modules — and the knowledge graph should reflect it. This covers…
wiki-status
Show the current state of the wiki — what's been ingested, what's pending, and the delta between sources and wiki content. Use this skill when the user asks "what's the status", "how much is ingested", "what's left to process", "show me the delta", "what changed since last ingest", "wiki dashboard", or wants an…
hermes-history-ingest
Ingest Hermes agent history into the Obsidian wiki. Use this skill when the user wants to mine their past Hermes sessions for knowledge, import their /.hermes folder, extract insights from previous Hermes conversations, or says things like "process my Hermes history", "add my Hermes memories to the wiki", "ingest…
wiki-narrate
Turn a wiki topic into a cited Markdown briefing, plain-language explanation, or progressive lecture. Use this skill for topic-based briefing, explanation, and lecture requests that must stay within the evidence compiled in an Obsidian vault.
wiki-context-pack
Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task. Use for "/wiki-context-pack", "use my vault as context", "context slice for X", "pack the wiki for my agent", or "bounded context for Y".