A project setting that controls how often the workflow asks for confirmation before acting. It supports cautious, default, and autonomous modes.

Use it to view or change the confirmation mode stored in .claude/dd-mode, which affects how /impl behaves.

It lets teams choose how much human approval routine or ambiguous work requires while keeping safeguards for destructive and high-stakes changes.

mode — Command by vrennat

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 commands/vrennat/developersdevelopers/mode

Clone the repo

git clone --depth 1 https://github.com/vrennat/developersDevelopers

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 532 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00045	$0.00532
Opus 5	$0.00023	$0.00266
Sonnet 5	$0.00009	$0.00106
Haiku 4.5	$0.00005	$0.00053

Measured yesterday against content hash 52cf3538a52c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mode 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 yesterday.

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.

commands/mode.md · 47 lines

What it actually says

/mode

Set the confirmation aggressiveness of /impl. Input is one of cautious, default, or autonomous. With no argument, report the current mode and stop.

Mode is stored at .claude/dd-mode (project-local, one word). The SessionStart hook reads it to state the active mode in ambient context, and /impl restates it at the top of every run.

Modes

Mode	Confirms on
`cautious`	Ambiguous tasks AND medium/complex tasks. For unfamiliar code or pre-release work — see the planned routing before execution even when the path is clear.
`default`	Ambiguous tasks only, regardless of complexity. The standard confirm-only-when-ambiguous behavior.
`autonomous`	Nothing routine. Even ambiguous tasks get a sensible stated default and proceed. Only destructive/irreversible ops (the CLAUDE.md escape hatch) still confirm.

Mode changes confirmation aggressiveness only. It does not touch the destructive-op escape hatch, and it does not touch stakes-gated review — a high-stakes change (auth, money, data) still gets an adversarial-reviewer pass in every mode.

Procedure

No argument: read .claude/dd-mode (treat absent as default) and print Mode: <mode> — <one-line behavior>. Stop.
Argument given: validate it is one of the three. If not, print the three valid options and stop without writing.

Write the bare word:

mkdir -p .claude && printf '%s\n' "<mode>" > .claude/dd-mode

Confirm: print Mode set: <mode> — <one-line behavior>. New sessions and the next /impl will use it.

Rules

The only filesystem write is .claude/dd-mode. Touch nothing else.
Consider adding .claude/dd-mode to .gitignore if the mode is a personal preference rather than a shared project setting.

Example

/mode autonomous
-> Mode set: autonomous — even ambiguous tasks get a sensible stated default and proceed; only destructive ops confirm. New sessions and the next /impl will use it.

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.

yesterday First seen · 47 lines · 45 tokens per session scan A 52cf3538a52c

Subscribe to this mod's changes

mode is a command published in the GitHub repository vrennat/developersDevelopers (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 532 once invoked, about $0.0002 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.

Productivity

mode

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/mode

Modes

Procedure

Rules

Example

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement