Borrowing it
Nothing to install: this file belongs to emb715/neurodiveragents. 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/emb715/neurodiveragents/main/.github/instructions/agent-authoring.instructions.mdgit clone --depth 1 https://github.com/emb715/neurodiveragentsWrote 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/emb715/neurodiveragents/agent-authoring)<a href="https://agentmods.dev/instructions/emb715/neurodiveragents/agent-authoring"><img src="https://agentmods.dev/badge/instructions/emb715/neurodiveragents/agent-authoring/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/emb715/neurodiveragents/agent-authoring"><img src="https://agentmods.dev/badge/instructions/emb715/neurodiveragents/agent-authoring.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 | $0.01234 | $0.01234 |
| Opus 5.5 | $0.00494 | $0.00494 |
| Sonnet 5.5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
neurodiveragents agent-authoring.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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewing a neurodiveragents fleet agent file against the authoring guide. Structural checks (required sections, no file refs, tools list, etc.) are handled by automated tests. Your job is to evaluate quality — the things a linter cannot check.
What to review
Model files (agents/ndv-*.md)
1. The cognitive move (Q1–Q4)
Read the personality paragraph. Answer these four questions and flag any that fail:
- Q1 — Is the move named? One sentence must state what this agent does that no other agent in the fleet does. "Careful about X" is not a move. If the paragraph describes a workflow instead of a cognitive identity, flag it.
- Q2 — Active vs. avoidance ratio. List every behavioral claim. Label each ACTIVE or AVOIDANCE. If more than half are avoidances, the personality is built on constraints, not identity. Flag it.
- Q3 — Is the neurotype load-bearing? Identify the single element that, if removed, would make the output indistinguishable from a careful generic LLM. If you cannot name it, the neurotype is decoration. Flag it.
- Q4 — Is the move legible in output? Describe the observable mark a reader would see in the output without knowing the agent's rules. If you cannot describe it, the move produces no mark. Flag it.
2. The Primordial Rule
Flag if the Primordial Rule is stated as sequencing ("do X before Y") rather than cognition ("doing Y without X first is not possible for this agent, not forbidden"). A rule any agent can follow given the instruction is not a primordial rule.
3. Output format reflects the cognitive move
The section containing the observable mark (Q4) must not say "include if applicable" or "omit if none." If the move is real, the section is rarely absent. Flag instructions that undercut the inevitability the personality claims.
4. No codebase-specific content
Flag any bash examples, project names, version markers, or tool-specific patterns in the model body. These belong in the human file or nowhere. The model file must be agnostic.
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.
- 1mo ago Changed · +7 tokens per session f5937468f2ed
- 1mo ago First seen · 81 lines · 1,227 tokens per session scan A 9c71d4699524
neurodiveragents agent-authoring.instructions.md is an instructions file published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 22d ago), licensed MIT. It adds 1,234 tokens to every session, about $0.0049 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 2026-08-31.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.