Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Mode

ASecurity

Show or switch the project's conformance mode between Enforced and À la carte, within the set the organization allows.

7 stars
0 votes
0 copies
1 views
Added 9/20/2026
ai-agentsgoshelldocumentation

Works with

cli

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add akka/ai-marketplace --skill mode --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mode?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Mode
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/akka-mode/badge)](https://www.skillsdirectory.com/skills/akka-mode)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: mode
description: "Show or switch the project's conformance mode between Enforced and À la carte, within the set the organization allows."
---

## User Input

You **MUST** consider the user input before proceeding (if not empty).

## Purpose

`/akka:mode` shows the project's conformance mode, or sets it. The mode is
recorded in `.akka/exit-conditions.yaml` and controls exactly one thing:
whether unmet exit conditions block shipping.

- **À la carte** — the default. The exit-condition set is **dormant** until the
  developer asks for it: only the Akka-intrinsic baseline resolves, no auditors
  are created, and nothing is captured. Once asked for, conditions are checked
  and shown but never block `/akka:ship`, which proceeds with an explicit
  override.
- **Enforced** — the full set applies from the start. `/akka:ship` refuses to
  release until every applicable condition is `green` and not stale, or covered
  by an effective waiver. You use sign-off, strike, and waive to resolve each
  `open` or `red` condition first.

Every Specify command is available in both modes; the mode changes what the
engine does on its own, not the command set. In Enforced mode the process gates
`PROC-AUDITOR-COVERAGE` and `PROC-ADEQUACY-REVIEWED` apply as usual. While the
set is dormant they do not resolve at all — there is nothing yet to have
covered or reviewed.

The organization can constrain this. A policy may set a different default and
lock it; when the mode is locked, only the org-allowed mode(s) may be set. A
locked Enforced mode cannot be dropped to À la carte to bypass the ship gate.

## Outline

1. **Parse the argument from `the user's request`.** Three cases:

   - **Empty** — this is a query. Skip to step 2 with no argument.
   - **`enforced` or `a-la-carte`** — pass through unchanged.
   - **A recognizable spelling of à la carte** — the documentation renders the
     mode as "À la carte", so accept `alacarte`, `a la carte`, `à-la-carte`,
     and `à la carte` and normalize them to `a-la-carte` before calling the
     CLI. The CLI accepts only the two canonical spellings.

   Anything else: stop and tell the user *"`/akka:mode` takes `enforced` or
   `a-la-carte`, or no argument to show the current mode."* Do not call the CLI.

2. **Invoke the CLI.** Run `akka specify mode` (with the normalized argument,
   if any) in the project directory, via the shell. With no argument it prints
   the effective mode and whether an org policy has locked it. With an argument
   it writes the mode to the project state and confirms.

3. **Answer the existing-conditions question, if it is asked.** Switching a
   project that already carries conditions and auditors to À la carte makes the
   CLI refuse and name the two options rather than decide for the developer.
   When that happens, ask the user plainly — *"This project already has checks
   set up. In À la carte they will not block shipping either way: do you want
   to keep checking them, or set them aside?"* — then rerun with
   `--exit-conditions=honor` or `--exit-conditions=ignore`. Nothing is deleted by `ignore`; the
   captured conditions stay in the project state and `--exit-conditions=honor` brings them
   back. A project with no conditions yet switches without any question.

4. **Handle an old CLI.** `akka specify mode` requires Akka CLI **3.0.70 or
   later**. Earlier versions expose only `akka specify init`, so the shell
   reports an unknown command. If that happens, do not report it as a project
   or policy problem — say the installed CLI is too old, show the installed
   version from `akka version`, and give the upgrade command for their
   platform (`winget upgrade Akka.Cli`, `brew upgrade akka`, or the curl
   installer).

5. **Report plainly.** State the mode in the user's terms — "Enforced" or
   "À la carte" — and say what it means for shipping. In À la carte, say
   whether the checks are dormant, being kept, or set aside. When the mode is
   locked by org policy, say that it is locked and by whom, and do not present
   the other mode as an option. When a set succeeded, say which mode is now in
   effect and that nothing else about the project changed.

## Key rules

- Never edit `.akka/exit-conditions.yaml` directly to change the mode. The CLI
  enforces the org policy; a hand-edit bypasses it.
- Never retry a refusal in another form. If the org policy rejected the mode,
  that is the answer — report it and stop.
- The mode does govern whether conditions are in play, but never silently. A
  dormant set is dormant because nobody asked for it, and a set aside one
  because the developer said so — describe which of the two it is rather than
  saying conditions were "turned off".
- `--exit-conditions=ignore` is not a delete. Never describe it as removing conditions or
  auditors; they persist in the project state and come back with `--exit-conditions=honor`.
- With no argument this command is read-only. Do not set a mode the user did
  not ask for, and do not "helpfully" switch modes as part of another command.
  Asking the existing-conditions question when the CLI refuses is not a mode
  switch of your own — it is completing the one the user asked for.

## Done When

- [ ] The argument was parsed from `the user's request` and either recognized as a
      query, normalized to `enforced` / `a-la-carte`, or rejected without
      calling the CLI.
- [ ] `akka specify mode` was invoked, and an unknown-command failure was
      reported as a CLI version problem with the upgrade instruction — never as
      a project or policy error.
- [ ] A refusal naming the existing conditions was turned into a plain question
      to the user, and the answer was applied by rerunning with `--exit-conditions=honor`
      or `--exit-conditions=ignore` — never decided on the user's behalf.
- [ ] The effective mode was reported plainly, along with what it means for
      shipping, and any org lock was stated as a lock rather than a choice.

Attribution

akkaakka
View sourceMore from akka →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →