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/qttrash/tarkov-map/agents-mdgit clone --depth 1 https://github.com/QTtrash/tarkov-mapWrote 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/qttrash/tarkov-map/agents-md)<a href="https://agentmods.dev/instructions/qttrash/tarkov-map/agents-md"><img src="https://agentmods.dev/badge/instructions/qttrash/tarkov-map/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 | $0.00353 | $0.00353 |
| Opus 5 | $0.00177 | $0.00177 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
tarkov-map 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 5d 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 guide
Raid Signal is a Windows Tauri application plus a separately deployed Node.js relay and static phone companion. Treat this file as an index; follow the linked documents instead of duplicating their details in prompts or code comments.
Start here
docs/ARCHITECTURE.md— runtime boundaries, data flow, and module ownership.docs/SECURITY.md— trust boundaries and invariants that changes must retain.docs/QUALITY.md— the one-command verification contract and test ownership.CONTRIBUTING.md— environment setup and pull-request expectations.ASSET_LICENSES.md— non-code asset scope, provenance, and restrictions.
Non-negotiable invariants
- Never read game memory, inject input, alter game files, or claim anti-cheat approval.
- Invitation keys stay in URL fragments and must never reach or be logged by the relay.
- The relay forwards ciphertext only and stores no position history.
- Keep existing settings schema v2 and room protocol v1 compatible.
- Do not commit installers, build outputs, secrets, personal deployment paths, or refreshed assets without their hashes and provenance.
- Validate data at every filesystem, storage, native-command, and network boundary before treating it as an application type.
Working loop
- Read the owning module and its nearest tests before editing.
- Keep behavior changes separate from formatting and structural extraction.
- Run the narrowest relevant test while iterating.
- Run
npm run check:allbefore handing work off. - Use a Conventional Commit pull-request title and explain why, compatibility, security/privacy impact, and validation in the body.
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.
- 5d ago First seen · 36 lines · 353 tokens per session scan A dc87f8a4f951
tarkov-map AGENTS.md is an instructions file published in the GitHub repository QTtrash/tarkov-map (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 353 tokens to every session, about $0.0018 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
anarlog AGENTS.md
AGENTS.md instructions for fastrepl/anarlog, covering commands, pre-commit verification, guidelines, code style and cli tui command architecture.
pinvou-agent AGENTS.md
AGENTS.md instructions for Pinvou/pinvou-agent, covering pinvou agent project conventions, core constraints, 0. local private memory, 1. development and pull request conventions and 2. codewhale and fork boundaries.
markra AGENTS.md
AGENTS.md instructions for markrahq/markra, covering markra engineering guidelines, package management, tech stack, code organization and codemirror editor invariants.
cowork-z CLAUDE.md
Claude Code instructions for kevinlin/cowork-z, covering claude.md, project overview, commands, architecture and multi-process overview.
Khaos-Brain AGENTS.md
Instructions for liuyingxuvka/Khaos-Brain, covering repository expectations, bootstrap, start here, purpose and github publish default.
MarkCardStudio AGENTS.md
AGENTS.md instructions for pangxiaobin/MarkCardStudio, covering repository guide for coding agents, product scope, stack and commands, architecture and important invariants.