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/polarity/app.spectrum.analyzer/htmlgit clone --depth 1 https://github.com/polarity/app.spectrum.analyzerWhat 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 | $0.00098 | $0.00098 |
| Opus 5 | $0.00049 | $0.00049 |
| Sonnet 5 | $0.00020 | $0.00020 |
| Haiku 4.5 | $0.00010 | $0.00010 |
Grade A, and why
app.spectrum.analyzer html.instructions.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 2d 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.
What it actually says
HTML Instructions
- Keep metadata tags, footer links, and the external stylesheet/module bootstrap intact unless the task explicitly changes them.
- Keep structure semantic and accessibility-aware.
- Avoid inline styles when the same presentation belongs in
style.css. - Keep control IDs synchronized with the selectors used in
uiController.jsandmain.js. - If a control is removed from the DOM, verify that the related JavaScript path is also updated.
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.
- 2d ago First seen · 11 lines · 98 tokens per session scan A 874f2968264f
app.spectrum.analyzer html.instructions.md is an instructions file published in the GitHub repository polarity/app.spectrum.analyzer (21 stars, last pushed 5mo ago), licensed MIT. It adds 98 tokens to every session, about $0.0005 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
librosa AGENTS.md
Instructions for librosa/librosa, covering agent interaction policy for librosa, 1. automated platform interactions, 2. exception for project-authorized automation and 3. machine-readable directive.
cc-3-8-x-mcp AGENTS.md
Instructions for HappyLifeOk/cc-3-8-x-mcp, covering agents.md, 允许入口, 绑定当前项目, gateway tool and 预览 url.
tilawa AGENTS.md
Instructions for yazinsai/tilawa, covering tilawa, layout, sdk architecture, public surface (@tilawa/core) and build & test the sdk.
elah AGENTS.md
Instructions for elahlabs/elah, covering agents.md, what this is, layout, commands and the export worker.
gmc64 CLAUDE.md
Instructions for needlestack/gmc64, covering gmc64 technical documentation, quick reference, project structure, architecture decisions and data architecture & serialization.
autodoubao AGENTS.md
AGENTS.md instructions for linxxcat000/autodoubao, covering autodoubao project instructions, durable context, using the mcp, browser constraints and verification.