ai-agent-memory lint.instructions.md

ai-agent-memory lint.instructions.md is an instructions file for GitHub Copilot from ozgurkarahan/ai-agent-memory. It costs 649 tokens per session, scanned A, original, MIT.

A health check for a personal knowledge wiki. It examines the wiki’s structure, pages, metadata, and internal links for problems.

In plain words
What is it for?
Use it when you say “lint,” “health check,” or “check wiki.” It reads the schema and catalogue, inventories wiki pages, builds a map of links, and checks for critical or important errors.
Why use it?
It finds broken links, missing page information, and other issues that can make a wiki harder to search and maintain. The checks use the wiki files directly.

Instructions file for GitHub Copilot

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 instructions/ozgurkarahan/ai-agent-memory/lint
Clone the repo
git clone --depth 1 https://github.com/ozgurkarahan/ai-agent-memory

Made for: GitHub Copilot.

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 ai-agent-memory lint.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ozgurkarahan/ai-agent-memory/lint.svg)](https://agentmods.dev/instructions/ozgurkarahan/ai-agent-memory/lint)
Your own site
<a href="https://agentmods.dev/instructions/ozgurkarahan/ai-agent-memory/lint"><img src="https://agentmods.dev/badge/instructions/ozgurkarahan/ai-agent-memory/lint.svg" alt="Measured on agentmods" height="20"></a>
Per session 649 This file is loaded in full into every session.
When invoked 649 The same file — it is already loaded in full.
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 $0.00649 $0.00649
Opus 5 $0.00324 $0.00324
Sonnet 5 $0.00130 $0.00130
Haiku 4.5 $0.00065 $0.00065

Measured 5d ago against content hash 3fa81c0dce8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-agent-memory lint.instructions.md 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 5d 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.

.github/instructions/lint.instructions.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lint Wiki — Agent-Native Health Check

When the user says "lint", "health check", or "check wiki", inspect the wiki directly with the agent's file listing, search, and read tools. This skill has no helper-script dependency.

Resolve the memory root

Before reading or writing:

  1. If memory/schema.md exists in the current workspace, set WIKI_ROOT to memory/.
  2. Else if schema.md exists in the current workspace, set WIKI_ROOT to the current directory.
  3. Else follow the memory-wiki path declared in the current project's AGENT.md.
  4. If none resolves to a folder containing both schema.md and index.md, report the missing path and stop. Do not guess.

All paths below are relative to WIKI_ROOT.

Procedure

  1. Read schema.md and index.md.
  2. Inventory all Markdown pages recursively under wiki/. Treat _index.md files as indexes, not content pages.
  3. Build a slug map from content-page filenames and extract every [[wikilink]] target, ignoring aliases (|...) and headings (#...).
  4. Run the checks below using the agent's native search/read capabilities:

Critical

  • Missing or malformed frontmatter — page does not start with a complete --- block or lacks title, category, date_created, or date_updated.
  • Broken wikilink — target slug does not resolve to a content page.
  • Orphan page — content page has no incoming wikilink from another page or index.
  • Invalid source reference — a source_docs: entry is non-empty but does not resolve to a file under raw/.

Important

  • Missing catalog entry — content page is absent from index.md.
  • Missing category index entry — when wiki/{category}/_index.md exists, it does not link the page.
  • Thin page — fewer than 50 prose words outside frontmatter and headings.
  • Cross-reference gap — two clearly related existing pages mention the same canonical entity but do not link to each other.

Informational

  • Duplicate or ambiguous slugs across category folders.
  • Stale pages whose date_updated is more than six months old.
  • Unlinked glossary terms that appear repeatedly in content.

Read the full file on GitHub · 66 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. 5d ago First seen · 66 lines · 649 tokens per session scan A 3fa81c0dce8b

Subscribe to this mod's changes

ai-agent-memory lint.instructions.md is an instructions file published in the GitHub repository ozgurkarahan/ai-agent-memory (8 stars, last pushed 1mo ago), licensed MIT. It adds 649 tokens to every session, about $0.0032 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.