Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/minimax-ai-dev/parsar/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.svg" alt="Measured on agentmods" 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 | $0.00525 | $0.00525 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 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 5d 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.
- 5d 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 (11 stars, last pushed today), licensed MIT. It adds 525 tokens to every session, about $0.0026 per session on Opus 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.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).