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/lisihao/solar/agents-mdgit clone --depth 1 https://github.com/lisihao/SolarWrote 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/lisihao/solar/agents-md)<a href="https://agentmods.dev/instructions/lisihao/solar/agents-md"><img src="https://agentmods.dev/badge/instructions/lisihao/solar/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 | $0.00791 | $0.00791 |
| Opus 5 | $0.00396 | $0.00396 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
Solar 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 3d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global Output Style Policy
Mandatory Response Format
Default to Claude-Code-style visual formatting for all non-trivial responses across all workspaces.
Use this structure unless the user explicitly asks for plain text:
- One-line headline
- Sectioned blocks
- At least one monospace box table using Unicode borders
- Optional monospace topology/flow diagram when relevant
- Ending lines:
当前问题：...下一步：...
Formatting Rules
- Prefer Chinese labels and concise wording.
- Keep columns aligned in monospace blocks.
- Use consistent status labels:
ok | warn | error | pending. - For missing fields, print
N/A. - Avoid prose-first answers; structure first.
Logic Change Safety Policy
This is a hard rule for Solar work.
- Do not change product logic, scheduling logic, report logic, analysis logic, fallback behavior, scoring rules, routing rules, quota rules, lease rules, or model-selection behavior unless the user explicitly asked for that specific change.
- Do not silently replace an intended model-driven, evidence-driven, or multi-source intelligence path with deterministic heuristics, keyword rules, mock analysis, synthetic summaries, or fallback guesses.
- If the correct model/evidence path is unavailable, blocked, rate-limited, or incomplete, surface the real state as
warnorerror; do not make the UI or report look successful. - If a proposed fix would alter behavior outside the reported bug, stop and state the tradeoff before editing.
- Bug fixes should be minimal, local, and reversible unless the user explicitly asks for a broader redesign.
- Every report insight that claims analysis must be backed by explicit evidence ids, source artifacts, model output, or verified runtime state. Otherwise mark it as missing, incomplete, or pending.
- For AI Influence, Tech Hotspot Radar, GitHub intelligence, YouTube intelligence, social monitoring, scheduler, operator pool, lease, quota, and APO/Solar Optimizer work: never invent a "good enough" deterministic substitute for the intended intelligence pipeline.
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.
- 3d ago First seen · 53 lines · 791 tokens per session scan A 3d933cf97e79
Solar AGENTS.md is an instructions file published in the GitHub repository lisihao/Solar (2 stars, last pushed 20d ago), licensed MIT. It adds 791 tokens to every session, about $0.0040 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 2026-08-31.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.