mimir: Instructions file for Claude Code

CLAUDE.md

mimir CLAUDE.md is an instructions file for Claude Code from FeatureFactory-io/mimir. It costs 3,444 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Mimir, a web platform where teams document software-development methods and let AI assistants query them.

In plain words
What is it for?
Use them when developing Mimir’s Django web app, its MCP server, playbooks, workflows, activities, agents, skills, phases, artifacts, or rules.
Why use it?
They explain the project’s architecture, data structure, and development rules so changes fit the existing system.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is FeatureFactory-io/mimir's own configuration. It tells Claude Code how to work on mimir 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 mimir configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FeatureFactory-io/mimir. 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/FeatureFactory-io/mimir/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/FeatureFactory-io/mimir

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 mimir CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/featurefactory-io/mimir/claude-md"><img src="https://agentmods.dev/badge/instructions/featurefactory-io/mimir/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,444 This file is loaded in full into every session.
When invoked 3,444 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 $0.03444 $0.03444
Opus 5.5 $0.01378 $0.01378
Sonnet 5.5 $0.00689 $0.00689
Haiku 4.5 $0.00344 $0.00344

Measured 2mo ago against content hash 9fcdffd4ce28, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mimir 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 2mo 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 · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Mimir Development Guide

What Is Mimir

Mimir is a self-evolving engineering playbook platform. It lets teams document, evolve, and leverage software development methodologies through a Django web UI and an MCP (Model Context Protocol) server that AI assistants query directly.

Two-part system:

  • FOB (this repo) — Django 5 app with SQLite, runs MCP server + web server concurrently
  • HOMEBASE (separate repo) — Django + HTMX, eventing → Neo4j graph DB, aggregates PIPs from FOBs

Key innovation: AI assistants can propose playbook improvements (PIPs) that engineers review and approve.

Current Status: Production-ready MVP with full CRUDLF for Playbooks, Workflows, Activities, Agents, Skills, Phases (as modeled), Artifacts (partial), and Rules (playbook-scoped, Activity M2M). MCP integration includes 50+ tools (including rule CRUDLF and set_activity_rules).


Architecture

Directory Layout

mimir/                        # Django project config (settings, urls, wsgi)
methodology/                  # Core Django app (models, services, views, templates)
  models/                     # Playbook, Workflow, Phase, Activity, Artifact, Skill, Agent, Rule, …
  services/                   # Business logic (shared by UI and MCP)
  views/                      # Thin Django view controllers
  utils/                      # markdown_renderer.py (Markdown + Mermaid)
mcp_integration/              # MCP server (thin wrappers over services)
  tools.py                    # MCP tool definitions (playbooks, workflows, activities, skills, rules, …)
  context.py                  # User context
  management/commands/mcp_server.py
accounts/                     # User auth
tests/
  unit/                       # Model and service unit tests
  integration/                # MCP tools, multi-model workflows
  e2e/                        # Playwright browser tests
docs/
  features/act-*/             # BDD Gherkin specs (source of truth for features)
  architecture/SAO.md         # System architecture overview (read before big changes)
  plans/                      # Per-feature implementation plans
  ux/                         # Design system, IA guidelines, user journey
.windsurf/
  rules/                      # 38 development convention rules
  workflows/FeatureFactory/   # Complete product development playbook (6 workflows)
    ESM/                      # Envision the System (7 activities)
    DTA/                      # Define Architecture (18 activities)
    DSP/                      # Deploy Software Process (6 activities)
    EST/                      # Estimate the Project (8 activities)
    BSP/                      # Bootstrap Project (8 activities)
    BPE/                      # Build Feature (8 activities)

Read the full file on GitHub · 341 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. 2mo ago First seen · 341 lines · 3,444 tokens per session scan A 9fcdffd4ce28

Subscribe to this mod's changes

mimir CLAUDE.md is an instructions file published in the GitHub repository FeatureFactory-io/mimir (16 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,444 tokens to every session, about $0.0138 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 2026-08-30.

Related

mimir CLAUDE.md compared with instructions from other repositories

mimir CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mimir CLAUDE.mdFeatureFactory-io/mimirInstructions file161mo agoApache-2.0A3,444Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, 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