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/rookslog/sophotron/agents-mdgit clone --depth 1 https://github.com/rookslog/sophotronWrote 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/rookslog/sophotron/agents-md)<a href="https://agentmods.dev/instructions/rookslog/sophotron/agents-md"><img src="https://agentmods.dev/badge/instructions/rookslog/sophotron/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 | $0.00170 | $0.00170 |
| Opus 5 | $0.00085 | $0.00085 |
| Sonnet 5 | $0.00034 | $0.00034 |
| Haiku 4.5 | $0.00017 | $0.00017 |
Grade A, and why
sophotron AGENTS.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 3d 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.
What it actually says
Agent instructions
The operational guide for this repo lives in CLAUDE.md — architecture, module conventions, correctness contracts, and the verification commands that define "done". It is harness-agnostic despite the name; read it in full before editing anything.
Also binding:
- CONTRIBUTING.md — workflow, review process, and the claims discipline for PR descriptions (state only what was actually run).
- docs/style-guide.md — for any public-facing prose you write, including PR descriptions.
Two rules worth repeating because violations are silent: stdout is the MCP transport (log to stderr only), and a transient upstream failure (429/5xx) must never be reported as a genuine empty result.
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.
- 3d ago First seen · 18 lines · 170 tokens per session scan A 314a77d4255f
sophotron AGENTS.md is an instructions file published in the GitHub repository rookslog/sophotron (0 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session, about $0.0009 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
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
foundry-local python-cffi-pointer-types.instructions.md
Use when working on the Python SDK's native bindings (cffi), especially when defining new Item subclasses, working with flItemQueue, or extending Request/Session methods that pass native handles.
experiencer CLAUDE.md
Claude Code instructions for vincentlaucsb/experiencer: The canonical repository instructions are in AGENTS.md. Read and follow that file; this compatibility entrypoint intentionally defines no independent rules.
pip-web CLAUDE.md
Claude Code instructions for playpip/pip-web, covering claude.md — agent guide for pip, read first (by task), the three layers (respect the boundaries), non-negotiables and commands / definition of done.
hashloom CLAUDE.md
Claude Code instructions for davet47/hashloom, covering working rules for hashloom, git is the user's, scope discipline, hashloom develops on hashloom and definition of done: >5x token reduction.
bitcoin-mcp copilot-instructions.md
Instructions for Bortlesboat/bitcoin-mcp, covering bitcoin-mcp copilot instructions, rules, satoshi api reference and verification.