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/zackabrah/scopeglass/agents-mdgit clone --depth 1 https://github.com/zackabrah/scopeglassWrote 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/zackabrah/scopeglass/agents-md)<a href="https://agentmods.dev/instructions/zackabrah/scopeglass/agents-md"><img src="https://agentmods.dev/badge/instructions/zackabrah/scopeglass/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 | $0.00424 | $0.00424 |
| Opus 5 | $0.00212 | $0.00212 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
scopeglass 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 4d 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
Scopeglass contributor instructions
Project
Scopeglass is a local-only Node.js/TypeScript CLI for inspecting hierarchical
AGENTS.md scope. The source of truth is SPEC.md; the ordered implementation
plan is tasks/plan.md.
Commands
- Install:
npm ci - Test:
npm test - Coverage:
npm run test:coverage - Lint:
npm run lint - Format check:
npm run format:check - Typecheck:
npm run typecheck - Build:
npm run build - Package check:
npm run package:check - Full verification:
npm run verify
Conventions
- Use TypeScript ESM and named exports in library modules.
- Keep the functional analysis core separate from filesystem/process boundaries.
- Validate external values once at the boundary; internal code relies on typed
contracts from
src/types.ts. - Write a failing behavioral test before implementation.
- Preserve stable JSON schema fields, diagnostic codes, and CLI exit codes.
- Keep repository-derived content visibly untrusted and escaped in every output.
- Prefer small focused modules and explicit data flow over framework patterns.
export function normalizeDisplayPath(
root: string,
absolutePath: string,
): string {
return path.relative(root, absolutePath).split(path.sep).join("/") || ".";
}
Boundaries
Always
- Resolve and contain paths before reading.
- Cap input sizes and test abuse cases.
- Run the relevant focused test after each behavior change.
- Run
npm run verifybefore declaring the release candidate complete.
Ask first
- Add a runtime dependency.
- Change public JSON, diagnostics, commands, or exit semantics.
- Add a new scanned instruction format or vendor profile.
Never
- Execute, import, or fetch content referenced by a scanned repository.
- Add telemetry, remote assets, model calls, or runtime network access.
- Use
innerHTMLwith repository-derived content. - Weaken or delete a failing test to make verification pass.
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.
- 4d ago First seen · 62 lines · 424 tokens per session scan A 645a2dd012e6
scopeglass AGENTS.md is an instructions file published in the GitHub repository zackabrah/scopeglass (2 stars, last pushed yesterday), licensed MIT. It adds 424 tokens to every session, about $0.0021 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
fastagent AGENTS.md
AGENTS.md instructions for fastagent-sh/fastagent, covering fastagent — agent guide, what this is, source of truth, repo map and devx principle stack.
trellis AGENTS.md
Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.
agentic-coding-workflow AGENTS.md
Instructions for abhilash-m96/agentic-coding-workflow, covering agentic coding workflow, rules, step 1 — understand the full scope, step 2 — propose the chunk plan and step 3 — write the finalised plan.
android-qa-kit AGENTS.md
Instructions for willbytee-sudo/android-qa-kit, covering agents.md — setting up and driving an android device, 1. how to work with the user, 2. start by finding out what's already there, 3. what you can do in each mode and 4. if there's no device: ask first.
agentscribe copilot-instructions.md
Instructions for Lucabiz/agentscribe, covering agentscribe, setup & commands, code style & conventions, testing and do not.
agentsmd CLAUDE.md
Claude Code instructions for youwei792/agentsmd, a project described as: CI for your AI agent's instructions — generate a grounded AGENTS.md, validate every command it references, audit token cost, bridge CLAUDE.md. Zero-dependency Go CLI.