wiki-maintain

A maintenance check for a Yarbrain wiki, a structured collection of notes and procedures. It finds structural errors, duplicates, stale knowledge, conflicts, unprocessed session evidence, and procedures that no longer match newer work.

In plain words
What is it for?
Use it for periodic wiki audits or when recall quality declines; it can produce reports and identify fixes, merges, archival, rechecking, or promotion to a procedure.
Why use it?
It helps keep the wiki trustworthy without automatically merging or deleting information that may still matter. Proposed content changes are presented for approval.

Skill for Claude CodeCodex

Part of the yarbrain plugin — 6 skills, 3 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/yarlson/yarstack/wiki-maintain
Any agent
npx skills add yarlson/yarstack --skill wiki-maintain
Clone the repo
git clone --depth 1 https://github.com/yarlson/yarstack

Made for: Claude Code, Codex.

Or install yarbrain, the plugin that ships this one along with the rest of its 6 skills, 3 hooks.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 425 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00054 $0.00425
Opus 5 $0.00027 $0.00212
Sonnet 5 $0.00011 $0.00085
Haiku 4.5 $0.00005 $0.00042

Measured 2d ago against content hash 70c209cf66b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-maintain 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 2d 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.

plugins/yarbrain/skills/wiki-maintain/SKILL.md · 41 lines

What it actually says

Maintain a Yarbrain Wiki

Keep the vault trustworthy without optimizing for fewer files or rewriting it for appearance.

Treat an audit request as read-only. Write a report, rebuild an index, or change vault content only when the user also authorizes maintenance.

Workflow

  1. Resolve ../../scripts/yarbrain.py relative to this SKILL.md and run lint. Record missing structure, duplicate IDs, missing provenance, and broken links before using model judgment.
  2. Count pending session records and identify episodes with no semantic or procedural consumer, notes past their freshness window, overlapping aliases, disputed claims, oversized index content, and skills contradicted by newer successful episodes.
  3. Classify each proposed change as fix-structure, merge, split, supersede, archive, reverify, or promote-procedure. Route procedure work to procedure-promote and semantic changes or disputes to wiki-reconcile. Leave ineligible procedure candidates unchanged and report them as deferred.
  4. Present every proposed mutation for approval, including structural fixes, semantic changes, index or report writes, and archival. Never delete the only copy of evidence or choose between credible conflicts without support.
  5. Apply only approved changes. Read every changed file back, rerun lint, and rebuild INDEX.md after canonical content is sound.
  6. Refresh reports/wiki-health.md with the check time, deterministic results, approved changes, unresolved conflicts, stale items, and pending counts.

Indexes and caches are rebuildable. Episodes are evidence. Canonical notes can evolve only through reconciliation. Keep those ownership rules intact during cleanup.

This version does not define an episode archival operation. Report unreferenced or old episodes as candidates, but do not move or delete them.

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. 2d ago First seen · 41 lines · 54 tokens per session scan A 70c209cf66b9

Subscribe to this mod's changes

wiki-maintain is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 425 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

opensrc

Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…

vercel-labs/opensrc · 103 tokens

release-cli

Release a new version of the tokenmaxxing CLI to npm. Use when explicitly asked to release or publish @851-labs/tokenmaxxing, including checking main, bumping apps/cli/package.json, updating CHANGELOG.md, committing, tagging cli-vX.Y.Z, pushing, monitoring generated native package publishing, and smoke testing the…

851-labs/tokenmaxxing · 73 tokens

ship-mobile-app

Build, change, debug, and prepare production mobile apps across domain meaning, local and server state, lifecycle, platform, and release boundaries. Use for non-trivial Flutter, React Native, iOS, or Android work involving persistence, sync, auth, offline behavior, notifications, permissions, native integrations…

aiopshwang/ship-mobile-app · 103 tokens

verify-regression-tests

Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…

aiopshwang/verify-regression-tests · 75 tokens

repository-bootstrap

Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.

cz1993/vibe-coding-repository-standard · 41 tokens

repository-hygiene

Perform a read-only evidence-based audit of stale docs, agent files, scripts, generated artifacts, duplicate code, and optional tools. Use only when explicitly asked for cleanup or governance review; do not delete or refactor during the audit.

cz1993/vibe-coding-repository-standard · 52 tokens