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/dawitlabs/capsule/claude-mdgit clone --depth 1 https://github.com/dawitlabs/capsuleWrote 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/dawitlabs/capsule/claude-md)<a href="https://agentmods.dev/instructions/dawitlabs/capsule/claude-md"><img src="https://agentmods.dev/badge/instructions/dawitlabs/capsule/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 | $0.00075 | $0.00075 |
| Opus 5 | $0.00037 | $0.00037 |
| Sonnet 5 | $0.00015 | $0.00015 |
| Haiku 4.5 | $0.00007 | $0.00007 |
Grade A, and why
capsule 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 4d 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.
This is a copy
100% identical to capsule AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Capsule Context
Before working in this repo:
- Read
.capsules/index.md. - Read the capsule matching the task area.
- Run
capsule stale <name>to check if sources changed. - If stale, inspect the changed files before editing.
- Update capsules when durable project knowledge 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.
- 4d ago First seen · 12 lines · 75 tokens per session scan A 1d650724bbff
capsule CLAUDE.md is an instructions file published in the GitHub repository dawitlabs/capsule (4 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to capsule AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
elephant-agent AGENTS.md
AGENTS.md instructions for agentic-in/elephant-agent, covering elephant agent entry, product north star, read first, non-negotiable rules and canonical commands.
elephant-agent copilot-instructions.md
Copilot instructions for agentic-in/elephant-agent, covering github copilot instructions, source of truth order, review priorities, harness-specific checks and validation expectations.
mnemic CLAUDE.md
Claude Code instructions for dongtang3/mnemic: This project includes a project-level .mcp.json for the Mnemic memory MCP server.
slimdex-mcp copilot-instructions.md
Copilot instructions for Siddhukaushik/slimdex-mcp, covering slimdex copilot instructions, find and read, write, memory and cost.
mnemic AGENTS.md
AGENTS.md instructions for dongtang3/mnemic: Mnemic is a graph-backed long-term memory substrate for coding agents and LLM applications.
ratel CLAUDE.md
Claude Code instructions for ratel-ai/ratel, a project described as: Context engineering for AI agents. 80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.