Borrowing it
Nothing to install: this file belongs to intentdriven/abcd. 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/intentdriven/abcd/main/AGENTS.mdgit clone --depth 1 https://github.com/intentdriven/abcdWrote 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/intentdriven/abcd/agents-md)<a href="https://agentmods.dev/instructions/intentdriven/abcd/agents-md"><img src="https://agentmods.dev/badge/instructions/intentdriven/abcd/agents-md/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/intentdriven/abcd/agents-md"><img src="https://agentmods.dev/badge/instructions/intentdriven/abcd/agents-md.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 | $0.07650 | $0.07650 |
| Opus 5.5 | $0.03060 | $0.03060 |
| Sonnet 5.5 | $0.01530 | $0.01530 |
| Haiku 4.5 | $0.00765 | $0.00765 |
Grade A, and why
abcd 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 today.
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 — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Conventions-file check word: brindlewort. A session that can name it without reading any file loaded this file as its instructions (itd-2610030814013772).
abcd rule loader
This repository uses the abcd modular rules loader. On UserPromptSubmit, a hook
recall-matches the prompt against keyword triggers declared in the plugin-bundled
default domains, the machine's ~/.abcd.noindex/rules.json and <repo>/.abcd/rules.json,
and injects only the matched domain rules into context — instead of
force-loading the full ruleset every turn.
A prompt that matches no domain injects nothing (zero added tokens).
- Inspect rules:
abcd rulesrenders the active set;abcd rules <DOMAIN>(case-insensitive) scopes to one domain. - Per-repo overrides: edit
<repo>/.abcd/rules.json. It is{"schema_version": 1, "disabled": false, "domains": {}}— add a domain key to override a default per-field (e.g.{"ROADMAP": {"state": "dormant"}}silences it while keeping its rules) or to declare a custom domain ({"recall": [...], "rules": [...]}). A domain left with no rules at all ({"rules": []}, or a custom domain declared without any) is SKIPPED with a diagnostic on stderr naming it — it would otherwise inject a heading-only block, which reads as a domain that says nothing. The rest of the file still loads;{"state": "dormant"}is the way to silence a domain deliberately. - Machine-wide overrides:
~/.abcd.noindex/rules.jsontakes the same schema and holds the conventions shared by every repo on the machine. The layers apply in order — bundled defaults, then~/.abcd.noindex/rules.json, then<repo>/.abcd/rules.json— each replacing a field wholesale, so the repo wins a field both set and a repodormantstate or kill switch holds against a user layer. The file is read only when it is a regular file this account owns that no one else can write, within 256 KiB; a file failing that, or failing to parse or validate, fails the load loudly and the hook injects nothing. Absent, it costs nothing and nothing is created; aHOMEor~/.abcd.noindexthis account cannot search reads as absent. A dotfiles-symlinked~/.abcd.noindexcan never host arules.json: the file is refused behind a symlinked~/.abcd.noindex, and only a symlinked~/.abcd.noindexwith norules.jsonin it is spared, reading as absent. - Provenance: a domain an override names (rules replaced, state changed, or a
custom domain) renders as
## NAME (user override)or## NAME (repo override), after the last layer that named it, wherever it appears: the injected block,abcd rules, and the hook's diagnostic;abcd rules --jsoncarries"source": "user"or"source": "repo"for it and"source": "bundled"for an untouched default. - Kill switch: set
"disabled": trueat the top of.abcd/rules.json; at the top of~/.abcd.noindex/rules.jsonit silences every repo on the machine, and no repo file re-enables it. - Foreign-uid roots: the loader and the shell guard read
.abcd/from the repository root resolved for the session, never from a directory above the working tree. Where git cannot answer for that tree — a checkout owned by another uid, a container bind mount — the root is recovered from the.gitmarker instead, and a root the caller does not own is REFUSED: the session takes its own working directory as the root, nothing above it is read, and one line on stderr names what was refused. The refusal bounds the walk, not the working directory: a.abcd/there is still read, so a session started AT the refused root reads that root's configuration, over~/.abcd.noindex/rules.jsonfor the rules. Re-admit such a checkout deliberately, from an account you control:mkdir -p ~/.abcd.noindex && printf '%s\n' '<checkout>' >> ~/.abcd.noindex/trusted-roots(one absolute path per line;#starts a comment). Only your home declares it — a file inside the checkout can never vouch for the checkout. - Explicit activation: start a prompt with
*<DOMAIN>(e.g.*COMMITTING,*PII) to inject that domain unconditionally — overrides adormantstate, but never the kill switch.
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.
- today Changed · +25 lines · +444 tokens per session 989837a0a857
- yesterday Changed · +15 lines · +289 tokens per session 82986fd3a970
- 5d ago Changed · +15 lines · +236 tokens per session 8fb6d4e19c25
- 6d ago Changed · -11 tokens per session cae13099f078
- 9d ago Changed · -149 lines · -2,810 tokens per session 0881e79830d8
- 11d ago Changed · +3 lines · +86 tokens per session b7cf1b1e27b2
- 13d ago Changed · +9 lines · +154 tokens per session 47e658d7413c
- 14d ago Changed · +14 lines · +260 tokens per session 2e7e6c76446c
- 15d ago Changed · +7 lines · +130 tokens per session 7b64fd1b2e3d
- 17d ago First seen · 527 lines · 8,872 tokens per session scan A 752918a02a79
abcd AGENTS.md is an instructions file published in the GitHub repository intentdriven/abcd (3 stars, last pushed today), licensed MIT. It adds 7,650 tokens to every session, about $0.0306 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).