agentmods.dev

mindgap: Instructions file for Claude Code

CLAUDE.md

mindgap CLAUDE.md is an instructions file for Claude Code from grburgess/mindgap. It costs 338 tokens per session, scanned A, original, MIT.

A project instruction file for Mindgap, a local knowledge graph that stores connected notes and research in a database.

In plain words
What is it for?
Use it when changing Mindgap, especially during knowledge-adding sessions, running tests, or working with its command-line tool and web interface.
Why use it?
It gives coding agents the project rules, commands, database locations, and testing instructions they need to work consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions AGENTS.md.

This is grburgess/mindgap's own configuration. It tells Claude Code how to work on mindgap itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mindgap configures →

not rated 0repo changed 23d ago A scan 338 tokens original MIT
View source ↗ grburgess/mindgap
Reuse

Borrowing it

Nothing to install: this file belongs to grburgess/mindgap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/grburgess/mindgap/development/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/grburgess/mindgap

Made for: Claude Code.

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 mindgap CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/grburgess/mindgap/claude-md/github.svg)](https://agentmods.dev/instructions/grburgess/mindgap/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/grburgess/mindgap/claude-md"><img src="https://agentmods.dev/badge/instructions/grburgess/mindgap/claude-md/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 mindgap CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/grburgess/mindgap/claude-md"><img src="https://agentmods.dev/badge/instructions/grburgess/mindgap/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 338 This file is loaded in full into every session.
When invoked 338 The same file — it is already loaded in full.
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 $0.00338 $0.00338
Opus 5.5 $0.00135 $0.00135
Sonnet 5.5 $0.00068 $0.00068
Haiku 4.5 $0.00034 $0.00034

Measured 23d ago against content hash e12e28766b4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mindgap CLAUDE.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 23d 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.

CLAUDE.md · 25 lines

What it actually says

mindgap

Local org-roam-style knowledge graph (SQLite + stdlib Python 3.10 + web UI). No pip deps.

  • Knowledge-adding sessions (loops) MUST read AGENTS.md first — it defines the ingest protocol.
  • CLI: mindgap (installed shim) or python3 -m mindgap from repo root.
  • DB: default ~/.mindgap/mindgap.db; env MINDGAP_DB (DB file) / MINDGAP_HOME (data dir) override.
  • Tests: python3 -m unittest discover tests.

Skills

  • mindgap-plugin/skills/ is the source of truth — edit the skills here.
  • They ship only through the plugin. Nothing is linked or copied into ~/.claude/ (no ~/.claude/skills/ symlinks); skills reference their own files by paths relative to the skill dir.
  • Learning ledgers live in $MINDGAP_HOME/learning/ (default ~/.mindgap/learning/), never in this repo.

Branching

  • development = integration branch (GitHub default). All PRs target development.
  • main = stable releases only; protected, no direct push.
  • Release: PR development→main that bumps version in pyproject.toml, mindgap-plugin/.claude-plugin/plugin.json, mindgap/mcp.py (+ tests/test_mcp.py); after merge tag vX.Y.Z on main.
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. 23d ago Changed · +8 lines · +122 tokens per session e12e28766b4d
  2. 2mo ago Changed · +8 lines · +88 tokens per session 824f18bd3288
  3. 2mo ago First seen · 9 lines · 128 tokens per session scan A 214ef2e93013

Subscribe to this mod's changes

mindgap CLAUDE.md is an instructions file published in the GitHub repository grburgess/mindgap (0 stars, last pushed 23d ago), licensed MIT. It adds 338 tokens to every session, about $0.0014 per session on Opus 5.5. 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

mindgap CLAUDE.md compared with instructions from other repositories

mindgap CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mindgap CLAUDE.mdgrburgess/mindgapInstructions file023d agoMITA338Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode