pith-wiki

pith-wiki is a skill for Claude Code from abhisekjha/pith. It costs 35 tokens per session (1,273 once invoked), scanned A, original, MIT.

A persistent wiki mode for maintaining a project knowledge base. A wiki is a collection of linked pages that records facts, concepts, decisions, sources, and unresolved questions.

In plain words
What is it for?
Use it to ingest information, update entity or concept pages, record decisions, query the wiki, and run its checks.
Why use it?
It keeps important decisions, bug fixes, and source material available for later work instead of leaving them only in chat.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - [source title](../raw/sources/file.md) — [date].

Part of the pith plugin — 12 skills, 4 commands, 4 hooks shipped together

Good fit Use it to ingest information, update entity or concept pages, record decisions, query the wiki, and run its checks.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/abhisekjha/pith
agentmods
npx agentmods add skills/abhisekjha/pith/pith-wiki

Made for: Claude Code.

Or install pith, the plugin that ships this one along with the rest of its 12 skills, 4 commands, 4 hooks.

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 pith-wiki

README.md
[![agentmods](https://agentmods.dev/badge/skills/abhisekjha/pith/pith-wiki/github.svg)](https://agentmods.dev/skills/abhisekjha/pith/pith-wiki)
Your own site
<a href="https://agentmods.dev/skills/abhisekjha/pith/pith-wiki"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-wiki/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 pith-wiki

Your own site · 80×15
<a href="https://agentmods.dev/skills/abhisekjha/pith/pith-wiki"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,273 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 $0.00035 $0.01273
Opus 5 $0.00017 $0.00636
Sonnet 5 $0.00007 $0.00255
Haiku 4.5 $0.00003 $0.00127

Measured 9d ago against content hash 6a958746f29d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pith-wiki 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 9d 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.

skills/pith-wiki/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wiki mode behavior

When wiki mode is active:

  • After significant decisions: offer to save to wiki
  • After bugs solved: offer to save resolution
  • After architecture discussions: offer to save as decision record
  • After ingest: show what was updated, ask for confirmation
  • Keep all offers brief: one line. User says yes/no.

Page formats

Entity page (person, company, tool, service, component)

# [Entity Name]

**Type:** person | org | tool | service | component
**Summary:** [2 sentences max]

## Key Facts
- [fact]
- [fact]

## Connections
- [[related-entity]] — [how they relate]

## Sources
- [source title](../raw/sources/file.md) — [date]

## Contradictions
- [claim in source A] vs [claim in source B] — unresolved

Concept page (idea, pattern, method, principle)

# [Concept Name]

**Definition:** [one sentence]
**Why it matters:** [one sentence]

## How it works
[2-4 sentences max]

## Related
- [[concept]] — [relation]

## Examples
- [concrete example]

## Open questions
- [what's still unclear]

## Sources
- [source](../raw/sources/file.md)

Decision record

# Decision: [what was decided]

**Date:** YYYY-MM-DD
**Status:** decided | revisiting | superseded

## Context
[1-2 sentences: why this decision was needed]

## Options considered
| Option | Pro | Con |
|--------|-----|-----|
| A | ... | ... |

## Decision
[what was chosen and single-sentence why]

## Consequences
- [what this enables]
- [what this constrains]

Synthesis / analysis page

# [Title]

**Thesis:** [one-sentence claim]
**Confidence:** high | medium | low

## Evidence
- [point] — [source](../raw/sources/file.md)

## Counter-evidence
- [point that argues against the thesis]

## Open questions
- [what would change this conclusion]

index.md format

One entry per wiki page. Updated on every ingest or new page.

# Wiki Index

## Entities
- [[EntityName]] — [one-line description] — [source count] sources

## Concepts
- [[ConceptName]] — [one-line description]

## Decisions
- [[Decision-title]] — [date] — [status]

## Syntheses
- [[Synthesis-title]] — [one-line thesis]

## Sources processed
- [Source Title](raw/sources/file.md) — [date ingested] — [pages updated]

Read the full file on GitHub · 214 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. 9d ago First seen · 214 lines · 35 tokens per session scan A 6a958746f29d

Subscribe to this mod's changes

pith-wiki is a skill published in the GitHub repository abhisekjha/pith (98 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,273 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.

Related

Other skills, from other repositories

agents-md-improver

Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or…

waybarrios/opencode-power-pack · 125 tokens

agents-md-revise

Capture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or local override) so future sessions benefit. Use when the user says "revise the rules", "update AGENTS.md / CLAUDE.md with what we just learned", "save this to project memory", "remember this for next time", or at the end…

waybarrios/opencode-power-pack · 114 tokens

cco-patterns

Share learned file patterns across a team — export an anonymized digest of what's usually waste/useful/co-edited, and import a teammate's so a fresh clone benefits day one.

egorfedorov/claude-context-optimizer · 39 tokens

team-memory-protocol

A shared-memory process for teams of coding agents working on the same build. It stores project knowledge, shared context, and task progress in separate files or repositories.

wigtn/wigtn-plugins · 42 tokens

knowledge-wiki

A tool that turns useful lessons from coding sessions into general articles for a team wiki. A wiki is a collection of linked reference pages, and this one can be kept locally or shared through a Git repository.

wigtn/wigtn-plugins · 97 tokens

dream

Prunes and consolidates the project's auto-memory to keep it minimal — deletes stale, wrong, or redundant memories, merges overlapping ones into existing files, and trims the index. Strong bias against growth: never creates new memory files and never stores new facts. Verifies staleness against the current codebase…

oprogramadorreal/optimus-claude · 85 tokens