Borrowing it
Nothing to install: this file belongs to MiniMax-AI-Dev/parsar. 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/MiniMax-AI-Dev/parsar/main/AGENTS.mdgit clone --depth 1 https://github.com/MiniMax-AI-Dev/parsarWrote 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/minimax-ai-dev/parsar/agents-md)<a href="https://agentmods.dev/instructions/minimax-ai-dev/parsar/agents-md"><img src="https://agentmods.dev/badge/instructions/minimax-ai-dev/parsar/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/minimax-ai-dev/parsar/agents-md"><img src="https://agentmods.dev/badge/instructions/minimax-ai-dev/parsar/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 | $0.00525 | $0.00525 |
| Opus 5.5 | $0.00210 | $0.00210 |
| Sonnet 5.5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
parsar 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parsar development protocol
This file is the agent-friendly shortcut. The canonical contributor
guide — including the hard rules, worktree workflow, architecture
baseline, web UI rules, and the required make check — lives in
CONTRIBUTING.md.
Architecture documentation
For any substantial implementation, refactor, runtime/process change, schema/API change, or cross-package behavior change:
- Read
CONTRIBUTING.mdbefore touching code. - Update
CONTRIBUTING.mdin the same branch when the change creates, removes, or clarifies an architecture rule, ownership boundary, workflow, required check, or generated artifact contract. - Do not let code establish a new convention that is absent from the contributor guide.
- Keep this file as a short agent-facing index. Put canonical long-form rules
in
CONTRIBUTING.md, and delete duplicated prose here instead of maintaining two copies.
Language
Except for user-facing internationalized bilingual copy, comments and documentation must be written in English.
Code quality
Full rules: CONTRIBUTING.md#code-quality--architecture.
Headlines:
- Split before you grow: Go files over ~500 lines / React components over ~400 lines are a signal to extract, not append to.
- Grep before you write: reuse an existing formatter / parser / error mapper instead of adding a near-duplicate one.
- One error-response helper per API surface — don't add another sentinel→status switch.
- Shared frontend logic (formatting, labels) lives once in
apps/web/src/lib/, never copy-pasted per page. server/internal/dev/routes.go,server/internal/store/store.go, andapps/web/src/pages/admin/AgentsPage.tsxare known oversized files — do not add more weight to them; split out the piece you're touching.
Generated contracts
Full rules: CONTRIBUTING.md#required-checks.
Headlines:
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 · 54 lines · 525 tokens per session scan A 63fe28e5ad7a
parsar AGENTS.md is an instructions file published in the GitHub repository MiniMax-AI-Dev/parsar (16 stars, last pushed 5d ago), licensed MIT. It adds 525 tokens to every session, about $0.0021 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.
parsar AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| parsar AGENTS.mdMiniMax-AI-Dev/parsar | Instructions file | 16 | 5d ago | MIT | A | 525 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| 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 ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |