What is d1v-cli AGENTS.md?

Repository instructions for d1v-cli that require planning work before editing and recording verification evidence before marking tasks complete. They define PLAN.md as the source of truth for scope, checks, and remaining risks.

Use them when planning non-trivial CLI changes, selecting validators, checking command help and exit behavior, and verifying stable JSON output.

They prevent an agent from treating code changes as finished before the relevant command behavior and automated output have been checked.

d1v-cli AGENTS.md — Instructions file by d1vai

Install

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.

agentmods

npx agentmods add instructions/d1vai/d1v-cli/agents-md

Clone the repo

git clone --depth 1 https://github.com/d1vai/d1v-cli

Made for: Codex, OpenCode.

Per session 935 This file is loaded in full into every session.

When invoked 935 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00935	$0.00935
Opus 5	$0.00467	$0.00467
Sonnet 5	$0.00187	$0.00187
Haiku 4.5	$0.00093	$0.00093

Measured 2d ago against content hash 6362d8abc936, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

d1v-cli 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 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.

AGENTS.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide (AGENTS.md)

Use this file as the execution contract for work in d1v-cli.

Planning First

Every non-trivial task must start by pruning stale or already-compressed completed items from PLAN.md, then writing the current goal, background, selected validators, and todo list before editing.
PLAN.md is the source of truth for scope, order, verification, evidence, and residual risk.
Keep at most one todo in_progress per execution thread unless work was intentionally delegated in parallel.

Checkoff Rule

Do not check off a todo until its assigned validators have passed and the evidence is written into PLAN.md.
If verification fails, keep the todo open, record the failure, and add the corrective next step.
Never mark work done based on implementation alone.

Minimum Verification Before Checkoff

@cli-ux-qa: before checking off a CLI UX todo, validate the final command shape, help text, flag names, exit semantics, and human-readable output against the intended user workflow.
@cli-json-qa: before checking off an automation-facing todo, confirm --format json returns stable machine-readable output and avoids leaking human-only hints into stdout.
@api-backend-qa: before checking off an API-integrated todo, run at least one local smoke command proving the happy path works, auth/error handling is correct, and returned data matches the expected shape.
@auth-state-qa: before checking off auth work, verify logged-out, logged-in, expired-token, and non-interactive flows.
@docs-adoption-qa: before checking off command-surface or workflow work, update the plan and command examples so a new CLI user can discover the path without reading source code.

Default Commands

cargo fmt --all
cargo test
cargo run -p d1v-cli -- --help
cargo run -p d1v-cli -- --format json debug

Treat failing formatting, tests, or help-output regressions as blockers and record any environment blocker in PLAN.md.

Rust Toolchain

Read the full file on GitHub · 64 lines

Changes

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 · 64 lines · 935 tokens per session scan A 6362d8abc936

Subscribe to this mod's changes

d1v-cli AGENTS.md is an instructions file published in the GitHub repository d1vai/d1v-cli (23 stars, last pushed 3d ago), licensed MIT. It adds 935 tokens to every session, about $0.0047 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.

Planning

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

d1v-cli AGENTS.md