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/navels/neal/agents-mdgit clone --depth 1 https://github.com/navels/nealWrote 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/navels/neal/agents-md)<a href="https://agentmods.dev/instructions/navels/neal/agents-md"><img src="https://agentmods.dev/badge/instructions/navels/neal/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 5.1 | $0.00994 | $0.00994 |
| Opus 5 | $0.00497 | $0.00497 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
neal 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 6d 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.
AGENTS.md
Instructions for AI coding agents working in this repository. Human contributors: see CONTRIBUTING.md.
What this is
neal is a TypeScript CLI: a plan-driven, multi-agent coding loop with
separate planner/coder/reviewer roles. Read
docs/architecture.md first for the run loop, state
model, and provider registry. The plan format, state machine, and prompt
contracts are all explicit and documented under docs/ — don't infer
behavior from folder structure or naming alone.
Setup and verification
corepack enable && corepack prepare pnpm@11 --activate && pnpm install
pnpm typecheck && pnpm lint && pnpm test && pnpm build && pnpm run verify:package
Run all five before calling anything done. pnpm test runs
NEAL_NOTIFY_BIN= node --import tsx --test test/*.test.ts; the suite needs
no live credentials or network access, and it must stay that way.
Gotchas that will silently break things
-
Two
typescriptinstalls, on purpose.typescript-7(an alias fortypescript@^7) drivespnpm build/pnpm typecheck; the plaintypescriptdependency stays pinned at^6becausetypescript-eslint's parser crashes on TypeScript 7's package (no classic compiler API). Don't "fix" this by unifying them. Seedocs/maintenance.md. -
Prompt builders are byte-pinned. Editing a file listed in
MATRIX_BUILDER_MODULES(test/prompt-render-integrity.test.ts) changes its SHA fingerprint. If the change alters rendered prompt output, bump the affectedPromptSpec.versioninsrc/neal/prompts/specs.ts, append a new golden undertest/fixtures/prompts/render-integrity/, and re-pin both the render SHA and the module SHA — never overwrite an existing versioned golden. If the live rendered output remains byte-identical, just re-pin the module SHA. Either way, run the focused test before opening a PR:NEAL_NOTIFY_BIN= node --import tsx --test test/prompt-render-integrity.test.ts -
"Consultant" and "adjudication" are different things. The consultant (
src/neal/adjudicator/consultant.ts) is the read-only role that triages a stuck run. The general adjudication framework (src/neal/adjudicator/,ADJUDICATION_SPECS) covers ordinary plan/execute/final-completion review and keeps the word "adjudication" — don't rename it to match the consultant, and don't call the consultant an "adjudicator" in user- or LLM-facing text. -
Native SDK bumps need live qualification, not just green CI.
@openai/codex-sdkand@anthropic-ai/claude-agent-sdkcan't be exercised in CI (no subscription auth there). Qualify withscripts/qualify-sdk.sh <pr-number>from a checkout with authenticated Claude/Codex CLIs before merging. Seedocs/maintenance.md.
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.
- 6d ago First seen · 81 lines · 994 tokens per session scan A a91fd9d6f009
neal AGENTS.md is an instructions file published in the GitHub repository navels/neal (21 stars, last pushed today), licensed MIT. It adds 994 tokens to every session, about $0.0050 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
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.
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.
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).