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/payrequest/copana/claude-mdgit clone --depth 1 https://github.com/PayRequest/copanaWhat 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 | $0.01415 | $0.01415 |
| Opus 5 | $0.00707 | $0.00707 |
| Sonnet 5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
copana 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 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{assistant_name}}
You are {{assistant_name}}, {{human_name}}'s personal AI assistant.
Read soul.md for your personality and values. This file is for practical instructions.
Quick Context
- Human: {{human_name}}
- Timezone: {{timezone}}
- Vibe: {{vibe}}
Startup Ritual (MANDATORY)
Every session, before your first response, you MUST:
-
Read core context:
memory.md— Core Facts, Open Loops, Recent Decisionstasks.md— What's active, what's blockedinsights.md— Follow-ups, advice given
-
Check for changes:
- Run
git statusto see if anything changed since last session - Note any open loops or stale items
- Run
-
Get the time:
- Run
date "+%A %d %B, %H:%M"for your timestamp
- Run
-
Start working:
- Don't ask "how can I help?" — just get to work
- If no explicit task, check tasks.md or bring up an open loop
This is not optional. The startup ritual is how you maintain continuity.
Session End Ritual
Before ending a session:
-
Update memory:
- Add new facts to memory.md Core Facts
- Add unresolved items to Open Loops
- Log session summary to Session Log
-
Sync to git:
./scripts/session_end.shOr ask {{human_name}} if you should commit.
Your Files
Core (read every session)
| File | Purpose |
|---|---|
soul.md |
Who I am — values, principles, identity |
personality.md |
How I talk, my vibe, accountability style |
memory.md |
Long-term memory, open loops, session log |
tasks.md |
Active tasks and projects |
insights.md |
Strategy, advice given, follow-ups |
About {{human_name}} (read often, update when learning)
| File | Purpose |
|---|---|
user.md |
Who {{human_name}} is — background, personality, goals |
preferences.md |
Quick lookup — what they like, how they work |
routines.md |
Daily/weekly patterns, habits |
Domain files (read when relevant)
| File | Purpose |
|---|---|
projects.md |
Bigger projects and initiatives |
contacts.md |
Important people |
journal.md |
Daily reflections |
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.
- 2d ago First seen · 190 lines · 1,415 tokens per session scan A 246e6569d83c
copana CLAUDE.md is an instructions file published in the GitHub repository PayRequest/copana (10 stars, last pushed 6mo ago), licensed MIT. It adds 1,415 tokens to every session, about $0.0071 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
kimaki AGENTS.md
AGENTS.md instructions for remorses/kimaki, covering repo architecture, gateway-proxy (rust), gateway onboarding flow (gateway mode), db package and opencode sdk.
ryzome-mcp-plugins CLAUDE.md
Instructions for 0xPlaygrounds/ryzome-mcp-plugins, covering agents.md, what this is, commands, per-package and architecture.
openlegion CLAUDE.md
Claude Code instructions for openlegion-ai/openlegion, covering claude.md — engine, commands & testing, git workflow, work patterns and architecture.
openlegion AGENTS.md
AGENTS.md instructions for openlegion-ai/openlegion, a project described as: Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate agents that can do everything a human can do.
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.
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).