Borrowing it
Nothing to install: this file belongs to Jercik/perplexity-agent-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/Jercik/perplexity-agent-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Jercik/perplexity-agent-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/jercik/perplexity-agent-mcp/agents-md)<a href="https://agentmods.dev/instructions/jercik/perplexity-agent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jercik/perplexity-agent-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/jercik/perplexity-agent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jercik/perplexity-agent-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 | $0.08657 | $0.08657 |
| Opus 5.5 | $0.03463 | $0.03463 |
| Sonnet 5.5 | $0.01731 | $0.01731 |
| Haiku 4.5 | $0.00866 | $0.00866 |
Grade A, and why
perplexity-agent-mcp AGENTS.md scanned grade A with 1 finding 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 12d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Default to `execFile` from `node:child_process`: the args array passes user input literally, so shell metacharacters cannot inject commands. Reach for a shell (`exec`, or `shell: true`) only for pipes, globs, or env expa How it starts
The opening of the file, as written. The whole thing — 623 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule: Read the Startup Files First
Read @README.md before taking any action.
Rule: Execute Commands from Arrays, Not Strings
Store commands in arrays, not strings
When Bash expands a string variable, quotes inside become literal characters and whitespace triggers word splitting:
# BAD
CMD="echo \"hello world\""
$CMD # outputs: "hello world" (with literal quotes)
# GOOD: array preserves argument boundaries
CMD=(echo "hello world")
"${CMD[@]}" # outputs: hello world
Never interpolate variables into shell strings
Variables interpolated into shell strings — sh -c, bash -c, eval, ssh host — are reparsed by the shell. Characters like $(...), backticks, or ; in the value execute as code — an injection vector:
# BAD: if VAR contains $(malicious), it executes
sh -c "$VAR --write"
# GOOD: direct execution, no shell interpretation
"${CMD[@]}" --write
# GOOD: with xargs, execute the array directly
find . -name '*.js' -print0 | xargs -0 "${CMD[@]}" --write --
When you need shell features (pipes, redirects), use the exec "$@" pattern to pass arguments as positional parameters instead of interpolating them:
# GOOD: arguments passed as $@, not interpolated into the string; the redirect is why sh -c is needed
find . -name '*.js' -print0 | xargs -0 sh -c 'exec "$@" >> format.log 2>&1' _ "${CMD[@]}" --write --
The _ occupies $0 (the script name), leaving $@ for the command and arguments.
Rule: Avoid Leaky Abstractions
Design interfaces around what callers need, not how the system works internally. An abstraction is leaky when using it correctly requires knowledge of underlying storage, infrastructure, or error behavior — a connection string in a method signature, a transaction handle in a return type, an error that only makes sense one layer down, or two similar-looking methods where one reads memory and the other crosses the network. Keep signatures consistent, return domain types instead of backend artifacts, and inject infrastructure dependencies through constructors rather than method parameters.
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.
- 12d ago Changed · -2 lines · -103 tokens per session 101fc4ea92f7
- 13d ago Changed · -11 tokens per session 8eefef8d29c3
- 14d ago Changed · +8 lines · +457 tokens per session 9a866867dcbe
- 1mo ago Changed · +8 lines · +389 tokens per session 2a7fd155c34d
- 2mo ago Changed · -41 lines · +1,190 tokens per session 3168ab96cf3d
- 2mo ago First seen · 650 lines · 6,735 tokens per session scan A 9af9250b22c3
perplexity-agent-mcp AGENTS.md is an instructions file published in the GitHub repository Jercik/perplexity-agent-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 8,657 tokens to every session, about $0.0346 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
perplexity-agent-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| perplexity-agent-mcp AGENTS.mdJercik/perplexity-agent-mcp | Instructions file | 1 | yesterday | MIT | A | 8,657 | 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 |