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.
npx agentmods add instructions/replikativ/simmis/claude-mdgit clone --depth 1 https://github.com/replikativ/simmisWrote 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.
[](https://agentmods.dev/instructions/replikativ/simmis/claude-md)<a href="https://agentmods.dev/instructions/replikativ/simmis/claude-md"><img src="https://agentmods.dev/badge/instructions/replikativ/simmis/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03743 | $0.03743 |
| Opus 5 | $0.01871 | $0.01871 |
| Sonnet 5 | $0.00749 | $0.00749 |
| Haiku 4.5 | $0.00374 | $0.00374 |
Grade A, and why
simmis 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 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.
How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. Refreshed 2026-07-03 — the previous version documented the retired UIx/React architecture.
What simmis is
A business-oriented, value-building, self-programming environment on the datahike.io stack: chat + wiki + knowledge bases + AI staff, one shared memory substrate. The UI is spindel (FRP signals/spins rendering DOM incrementally — NOT React); the agent substrate is dvergr (discourse rooms, SCI sandbox, per-room scheduler, telegram channel); persistence is datahike over konserve with yggdrasil CoW branching, synced client↔server via konserve-sync over kabel websockets with kabel-auth JWT.
simmis is the prime showcase for spindel — hold UI code to idiomatic reactive decomposition (see "spindel sharp edges" below).
Documentation: doc/architecture.md first, then doc/data-model.md,
doc/authority.md, doc/proposals-and-time-travel.md, doc/agents.md.
Each describes code that exists; there is no roadmap or backlog in the
repository, and open work is not tracked in documentation.
Instructions
- Use
clj-nrepl-evalto iterate and validate before large changes. - Avoid fallback solutions except for experimentation; ask when you can't solve something without one.
- Git commit after significant milestones; not while stuck or debugging.
- Circle back to
doc/after an implementation and before committing. Those five documents describe code that EXISTS — if a change makes one of them wrong, fix it in the same commit rather than adding a note about it. - When isolating a problem is hard, add log statements / REPL probes. For reactive-correctness bugs, trace ENGINE state via REPL probes — not app-level workarounds.
NEVER Use Delays as Patches
Never use setTimeout/Thread/sleep/timeouts to "fix" timing or
synchronization issues. Use real coordination: await events, channels,
promises, signals, or pass data explicitly. (One legitimate exception:
a requestAnimationFrame to defer DOM measurements until after tree
linkage — a documented DOM lifecycle idiom, not a race patch.)
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.
- 5d ago First seen · 315 lines · 3,743 tokens per session scan A 3421c154b4ce
simmis CLAUDE.md is an instructions file published in the GitHub repository replikativ/simmis (5 stars, last pushed 3d ago), licensed MIT. It adds 3,743 tokens to every session, about $0.0187 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.