Borrowing it
Nothing to install: this file belongs to rix1337/Quasarr. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rix1337/Quasarr/main/AGENTS.mdgit clone --depth 1 https://github.com/rix1337/QuasarrWrote 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/rix1337/quasarr/agents-md)<a href="https://agentmods.dev/instructions/rix1337/quasarr/agents-md"><img src="https://agentmods.dev/badge/instructions/rix1337/quasarr/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/rix1337/quasarr/agents-md"><img src="https://agentmods.dev/badge/instructions/rix1337/quasarr/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01281 | $0.01281 |
| Opus 5.5 | $0.00512 | $0.00512 |
| Sonnet 5.5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
Quasarr 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quasarr working rules
Highest-priority rules
These rules take priority over all Trail decisions and other repository guidance:
- Always use Trail commands first to investigate this repository. Use its map, search, signatures, and caller graph before ordinary source searches or file reads. Use ordinary tools afterward only for unindexed material or missing detail. If Trail is not installed, stop repository work and ask the user to install it with
npm install -g @trailhq/trail-code. Do not install it yourself or continue without it. - Never name, hardcode, or commit real source hostnames. Never add one to any file that is not gitignored, including Trail knowledge, tests, comments, generated assets, captures, and temporary scripts. Source hostnames belong only in encrypted runtime configuration outside the repository. Refer to sources by their two-letter uppercase identifiers.
- Before finalizing changes or pushing, run
uv run python -X utf8 pre-commit.py. Accept and keep its edits, including formatting, dependency upgrades, lockfile changes, and version bumps. Do not revert them as unrelated changes. Re-run after history rewrites before pushing.
Privacy
Privacy checks protect repository content; do not add runtime sandboxes or network restrictions as part of this workflow.
- Never commit credentials, webhook endpoints/tokens,
.env, real release titles or URLs, personal names, emails, machine identifiers, or local absolute paths. Use synthetic titles and reserved.invaliddomains in examples and tests. Existing public service identifiers required by production matching are not source-hostname examples. - Before changing a source request, parser, or matching rule, obtain real traffic evidence: user-provided Proxyman captures or direct requests to the configured source. Do not infer payloads or response shapes. Keep raw evidence gitignored; save only sanitized architectural conclusions.
- Do not probe direct hoster links for liveness. JDownloader owns hoster verification, authentication, and downloads.
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 Changed · +63 tokens per session 42cdcd6d4f5a
- 5d ago Changed · -2 lines · -67 tokens per session 917094b04066
- 19d ago Changed · -140 lines · -2,197 tokens per session a7d2e13007e6
- 20d ago Changed · +46 tokens per session 390fd860152a
- 22d ago Changed · +11 lines · +482 tokens per session 344094591f2e
- 1mo ago Changed · +2 lines · +69 tokens per session 6c4b5ba42a2e
- 2mo ago First seen · 187 lines · 2,885 tokens per session scan A f9b1ec187f67
Quasarr AGENTS.md is an instructions file published in the GitHub repository rix1337/Quasarr (166 stars, last pushed yesterday), licensed MIT. It adds 1,281 tokens to every session, about $0.0051 per session on Opus 5.5. 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 2026-08-30.
Quasarr AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Quasarr AGENTS.mdrix1337/Quasarr | Instructions file | 166 | yesterday | MIT | A | 1,281 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |