Borrowing it
Nothing to install: this file belongs to thesammykins/FlixBridge. 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/thesammykins/FlixBridge/main/AGENTS.mdgit clone --depth 1 https://github.com/thesammykins/FlixBridgeWrote 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/thesammykins/flixbridge/agents-md)<a href="https://agentmods.dev/instructions/thesammykins/flixbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/thesammykins/flixbridge/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/thesammykins/flixbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/thesammykins/flixbridge/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 | $0.00733 | $0.00733 |
| Opus 5.5 | $0.00293 | $0.00293 |
| Sonnet 5.5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
FlixBridge 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 11d 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.
Contributing to FlixBridge
Work on the intended artifact
- Keep service-owned checkouts and unrelated changes intact; use an isolated worktree.
- Node.js 20+ is required. CI verifies Node 20, 22 and 24; it does not publish.
- Install with
npm ci --include=dev --ignore-scripts. Runtime gates arenpm run build,npm run check, andnpm test(unit runner plus MCP wire/client tests). - Rebuild and reconnect deliberately: editing source does not refresh an existing
process or npm installation. Server version comes from
package.json. - Live scripts contact configured services. Inspect them and obtain separate authority; never prove a development change with production mutations.
Preserve the operational contract
src/index.tsowns schemas, dispatch, envelopes and confirmations. Preserve tool names and required inputs; document additions and changed semantics.src/config.tsowns environment-only configuration;src/services/registry.tsseparates ARR instances from SABnzbd. Do not add file configuration implicitly.- Shared ARR behavior lives in
src/services/shared.ts; adapters own reviewed differences. HTTP goes throughsrc/core.tsfor limits, cancellation and errors. - Sonarr policy is per instance: omission stays legacy-v3, explicit pins verify,
and
autofollows reviewed maps insrc/services/arr/sonarr.ts. Freeze workflow family, preserve URL prefixes, and never replay writes across families after failure. Strict v5 rejects unported workflows before mutation. Statistics must not scan v3. - Keep stdout MCP-only and stderr for logs. Preserve SDK
serveStdiolegacy serving and the current-version guard until SDK wire tests make that guard redundant. Propagate cancellation through HTTP/body reads and verification delays. - Align schemas and validation: unknown-field rejection, literal IDs, bounds, conservative mutation annotations and matching structured/text output.
Mutations need evidence
- Diagnostics stay read-only by default. Single-use expiring tokens bind scope/options/ plans; they are not consent, locks or durable replay prevention.
- Refresh imports before submission and prove media/path/download identity. Retain downloads when commands or end-state verification are pending or incomplete.
- Keep legacy failed counts/status alongside additive pending evidence. Accepted work,
queue disappearance and
Pending:comments do not prove playback success. - Preserve partial aggregate data/errors. Empty pages with positive totals, ambiguous IDs and missing readbacks cannot prove absence or a clean stack.
- Plex destruction needs a unique exact media/file target and rederived token plan. Read media and comment outcomes separately. Retained account/client ownership protects replay across tool calls, but process-local guards die on restart or server reconstruction; token rotation creates a distinct configured identity.
- See safe usage and security limits.
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.
- 11d ago Changed · -413 lines · -4,117 tokens per session 40619febfc28
- 1mo ago First seen · 471 lines · 4,850 tokens per session scan A 212a99ec5e78
FlixBridge AGENTS.md is an instructions file published in the GitHub repository thesammykins/FlixBridge (1 stars, last pushed 2d ago), licensed MIT. It adds 733 tokens to every session, about $0.0029 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.