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/nosmoht/talos-mcp-server/agents-mdgit clone --depth 1 https://github.com/Nosmoht/talos-mcp-serverWrote 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/nosmoht/talos-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/nosmoht/talos-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/nosmoht/talos-mcp-server/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 5.1 | $0.08023 | $0.08023 |
| Opus 5 | $0.04012 | $0.04012 |
| Sonnet 5 | $0.01605 | $0.01605 |
| Haiku 4.5 | $0.00802 | $0.00802 |
Grade E, and why
talos-mcp-server AGENTS.md scanned grade E with 2 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 6d 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.
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.
4. **Re-read all comments** — if your comment is NOT the earliest `<!-- agent-claim:` comment by creation timestamp, another agent claimed first. Post and stop: ``` <!-- agent-unclaim: {session-id} --> Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
git config --global user.signingkey ~/.ssh/id_ed25519.pub How it starts
The opening of the file, as written. The whole thing — 628 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Machine-readable conventions for AI agents working on the talos-mcp repository. Read this file before starting any work.
Overview
Multiple AI agents (Claude Code, OpenAI Codex, GitHub Copilot, Cursor, and others) may work concurrently on this repository via git worktrees. This document defines:
- Coding conventions — how to write consistent Go code
- Workflow conventions — how to discover work, claim issues, and coordinate
Scope And Source Of Truth
AGENTS.md is the canonical cross-agent instruction file for this repository.
For this repo it carries the durable instructions every coding agent needs:
- Project purpose and repository-specific boundaries
- Build, test, lint, and verification commands
- Coding, testing, logging, and security conventions
- Multi-agent worktree, issue, commit, review, and PR workflow
- The split between agent instructions and human/operator documentation
CLAUDE.md is the Claude-Code-specific operative layer. It carries Claude-only
guidance (memory hygiene, review-artifact paths under .claude/) plus
quick-reference excerpts that link back here via Markdown links. Do not duplicate
cross-agent policy into CLAUDE.md — update AGENTS.md so the rule applies to
Claude Code, Codex, Copilot, Cursor, and other agents alike.
README.md is the human/operator entry point. Product usage, installation,
configuration, tool catalogs, compatibility tables, release notes, and end-user
examples live in README.md or purpose-built docs, not in AGENTS.md.
If nested AGENTS.md files are added later, the closest file to the edited path
wins for that subtree. Explicit user instructions in chat override this file.
Do not put in AGENTS.md
- Secrets, tokens, credentials, or machine-local private state
- One-off investigation notes, transient TODOs, command output, or scratch plans
- Detailed product/user documentation that belongs in
README.md - Claude-only subagent prompts, memory notes, or UI-specific instructions
- Long release postmortems or issue-specific analysis
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.
- 6d ago First seen · 628 lines · 8,023 tokens per session scan E 71b210a0ad17
talos-mcp-server AGENTS.md is an instructions file published in the GitHub repository Nosmoht/talos-mcp-server (2 stars, last pushed 12d ago), licensed MIT. It adds 8,023 tokens to every session, about $0.0401 per session on Opus 5. A static security scan graded it E with 2 findings (hidden instructions, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
arkade AGENTS.md
AGENTS.md instructions for alexellis/arkade, covering types of arkade commands, 1. how to add a new cli (tool) to arkade, what can be added, prerequisites and step 1: check github releases.
timoni AGENTS.md
AGENTS.md instructions for stefanprodan/timoni, covering agents.md, what timoni is, common commands, architecture and cmd/timoni/ — cli (cobra).
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
netdata CLAUDE.md
Claude Code instructions for netdata/netdata, a project described as: The fastest path to AI-powered full stack observability, even for lean teams.
siclaw AGENTS.md
AGENTS.md instructions for scitix/siclaw, covering siclaw project instructions, project shape, before risky edits, verification and stable boundaries.
infra CLAUDE.md
Claude Code instructions for anthr76/infra, covering claude.md, repository overview, development environment, common commands and task automation.