Borrowing it
Nothing to install: this file belongs to mishamyrt/perplexity-web-api-mcp. 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/mishamyrt/perplexity-web-api-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/mishamyrt/perplexity-web-api-mcpWrote 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/mishamyrt/perplexity-web-api-mcp/agents-md)<a href="https://agentmods.dev/instructions/mishamyrt/perplexity-web-api-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mishamyrt/perplexity-web-api-mcp/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/mishamyrt/perplexity-web-api-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mishamyrt/perplexity-web-api-mcp/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 | $0.00507 | $0.00507 |
| Opus 5.5 | $0.00203 | $0.00203 |
| Sonnet 5.5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
perplexity-web-api-mcp 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 2mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Guidelines for AI Agents
This repository is a Rust workspace with async code (Tokio-based). Use these rules when making changes.
Workspace & dependencies
- Prefer adding dependencies at the workspace root
Cargo.tomlunder[workspace.dependencies]. - In crate
Cargo.tomlfiles, reference them via workspace dependency resolution:dep = { workspace = true }dep = { workspace = true, features = ["..."] }
- Keep versions centralized in the workspace; avoid per-crate version drift.
- Only enable features you need; document why new deps/features are required.
Async Rust best practices (Tokio)
- Never block the runtime: avoid
std::thread::sleep, blocking IO, heavy CPU work on async tasks.- If unavoidable, use
tokio::task::spawn_blocking(and keep the critical section small).
- If unavoidable, use
- Propagate cancellation: respect
.awaitcancellation and avoid “fire-and-forget” unless justified.- Prefer structured concurrency (
JoinSet,try_join!) and ensure tasks are joined/dropped cleanly.
- Prefer structured concurrency (
- Add timeouts to external IO (
tokio::time::timeout) where hangs are possible. - Limit concurrency and backpressure: prefer bounded channels/streams; avoid unbounded buffering.
- Prefer explicit lifetimes/ownership and minimal cloning; use
Arcintentionally. - Avoid
unwrap()/expect()in library/runtime paths; return typed errors instead. - Keep public APIs small and well-documented; maintain backwards-compatible behavior unless required.
Error handling & logging
- Use structured errors (
thiserror/custom enums) and include actionable context. - Preserve sources (
#[source],std::error::Error::source) for troubleshooting. - Use structured logging (
tracing) and avoid leaking secrets (API keys, cookies, tokens).
Code style & project hygiene
- Match existing patterns in each crate (
client,parse,sse,upload, etc.). - Prefer small, testable functions; add unit/integration tests for non-trivial behavior changes.
- Update docs/examples when API behavior changes.
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.
- 2mo ago First seen · 48 lines · 507 tokens per session scan A 0b125eb4acb6
perplexity-web-api-mcp AGENTS.md is an instructions file published in the GitHub repository mishamyrt/perplexity-web-api-mcp (107 stars, last pushed 6mo ago), licensed MIT. It adds 507 tokens to every session, about $0.0020 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.
perplexity-web-api-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| perplexity-web-api-mcp AGENTS.mdmishamyrt/perplexity-web-api-mcp | Instructions file | 107 | 6mo ago | MIT | A | 507 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |