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/michael-obele/sepia/agents-mdgit clone --depth 1 https://github.com/Michael-Obele/sepiaWrote 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/michael-obele/sepia/agents-md)<a href="https://agentmods.dev/instructions/michael-obele/sepia/agents-md"><img src="https://agentmods.dev/badge/instructions/michael-obele/sepia/agents-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 | $0.02385 | $0.02385 |
| Opus 5 | $0.01192 | $0.01192 |
| Sonnet 5 | $0.00477 | $0.00477 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade C, and why
sepia AGENTS.md scanned grade C with 1 finding 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 today.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Source of truth: src/instructions.ts (MEMORY_CONTRACT). Keep in sync. --> The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- today Changed · +12 lines · +274 tokens per session b97553429e0d
- 4d ago First seen · 162 lines · 2,111 tokens per session scan C e0d94148bfb5
sepia AGENTS.md is an instructions file published in the GitHub repository Michael-Obele/sepia (3 stars, last pushed today), licensed AGPL-3.0. It adds 2,385 tokens to every session, about $0.0119 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ssd-ai memory-bank.instructions.md
Instructions for ssdeanx/ssd-ai, covering memory bank, memory bank structure, core files (required), additional context and core workflows.
flyto-core AGENTS.md
AGENTS.md instructions for flytohub/flyto-core, covering flyto-core agent rules, flyto2 project memory contract, flyto2 frontend quality gate and repo notes.
sveltest AGENTS.md
AGENTS.md instructions for spences10/sveltest, covering agents.md, unbreakable rules, essential commands, development and testing.
daz-mcp-server CLAUDE.md
Claude Code instructions for bluemoonfoundry/daz-mcp-server, covering claude.md (project index), primary commands, skill modules (reference with @), architecture summary and render api (dazscriptserver native endpoints).
state-memory-mcp copilot-instructions.md
Instructions for putervision/state-memory-mcp, covering state memory (state-memory-mcp), 1. priority order, 2. when to write to the graph, 3. workflow pattern and 4. codebase seeding on initialization.
mcp-router CLAUDE.md
Claude Code instructions for mcp-router/mcp-router, a project described as: A Unified MCP Server Management App (MCP Manager).