acm-config

acm-config is a skill for Claude Code from povvo/claudikins-automatic-context-manager. It costs 50 tokens per session (1,211 once invoked), scanned B, original, MIT.

An interactive configuration skill changes how Claudikins Automatic Context Manager handles context handoffs during Claude Code sessions.

In plain words
What is it for?
Use it to configure the trigger threshold, snooze duration, and summary length, including through the /acm:config command.
Why use it?
It lets you adjust when handoff warnings appear, how long they are postponed, and how much summary is created.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the claudikins-automatic-context-manager plugin — 2 skills, 1 command, 2 hooks shipped together

Good fit Use it to configure the trigger threshold, snooze duration, and summary length, including through the /acm:config command.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/povvo/claudikins-automatic-context-manager/acm-config
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.

Any agent
npx skills add povvo/claudikins-automatic-context-manager --skill acm-config
Clone the repo
git clone --depth 1 https://github.com/povvo/claudikins-automatic-context-manager

Made for: Claude Code.

Or install claudikins-automatic-context-manager, the plugin that ships this one along with the rest of its 2 skills, 1 command, 2 hooks.

Wrote 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.

agentmods badge for acm-config

README.md
[![agentmods](https://agentmods.dev/badge/skills/povvo/claudikins-automatic-context-manager/acm-config/github.svg)](https://agentmods.dev/skills/povvo/claudikins-automatic-context-manager/acm-config)
Your own site
<a href="https://agentmods.dev/skills/povvo/claudikins-automatic-context-manager/acm-config"><img src="https://agentmods.dev/badge/skills/povvo/claudikins-automatic-context-manager/acm-config/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.

agentmods 80×15 button for acm-config

Your own site · 80×15
<a href="https://agentmods.dev/skills/povvo/claudikins-automatic-context-manager/acm-config"><img src="https://agentmods.dev/badge/skills/povvo/claudikins-automatic-context-manager/acm-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,211 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.01211
Opus 5 $0.00025 $0.00606
Sonnet 5 $0.00010 $0.00242
Haiku 4.5 $0.00005 $0.00121

Measured 12d ago against content hash 59cb9f7f25ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

acm-config scanned grade B with 1 finding 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 12d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/claudikins-acm.conf
skills/acm-config/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claudikins Automatic Context Manager Interactive Configuration

You are helping the user configure Claudikins Automatic Context Manager. This skill guides you through an interactive configuration process where you ask the user questions and save their preferences to ~/.claude/claudikins-acm.conf.

Configuration Flow

Follow this conversational flow to configure Claudikins Automatic Context Manager:

1. Welcome & Current Settings

First, check if a config file exists and show current settings:

# Check for existing config
if [ -f ~/.claude/claudikins-acm.conf ]; then
    echo "Current Claudikins Automatic Context Manager Configuration:"
    cat ~/.claude/claudikins-acm.conf
else
    echo "No configuration found. Let's set up Claudikins Automatic Context Manager!"
fi

2. Ask Configuration Questions

Ask the user about each setting in a friendly, conversational way:

Context Trigger Threshold:

  • Question: "At what context percentage should the handoff dialog appear?"
  • Default: 60
  • Valid range: 50-90
  • Explain: "This controls when Claudikins alerts you. Lower = more frequent alerts, higher = fewer alerts but less context headroom."

Snooze Duration:

  • Question: "How long should the snooze duration be (in minutes)?"
  • Default: 5
  • Valid range: 1-60
  • Explain: "When you click 'SNOOZE', how long should Claudikins wait before asking again?"

Summary Token Length:

  • Question: "How detailed should handoff summaries be (in tokens)?"
  • Default: 500
  • Valid range: 200-2000
  • Explain: "Larger = more detailed summaries but takes longer to generate. 500 is usually perfect."

Dialog Style:

  • Question: "Which dialog style do you prefer?"
  • Options: "vibrant" (colorful, current default) or "minimal" (subtle colors)
  • Default: vibrant
  • Explain: "Vibrant uses bright orange/pink colors. Minimal uses muted tones."

3. Validate Input

For each answer:

  • Ensure values are within valid ranges
  • If invalid, explain why and ask again
  • Provide examples of good values

Read the full file on GitHub · 162 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.

  1. 12d ago First seen · 162 lines · 50 tokens per session scan B 59cb9f7f25ff

Subscribe to this mod's changes

acm-config is a skill published in the GitHub repository povvo/claudikins-automatic-context-manager (14 stars, last pushed 7mo ago), licensed MIT. It adds 50 tokens to every session and 1,211 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

obsidian-companion

Use when interacting with the user's Obsidian vault — reading, writing, searching, or chatting with notes using local RAG. Guides tool selection and writing strategy for all vault operations.

thoreinstein/obsidian-rag · 42 tokens

whats-up

Fetch recent activity from Autographical — what the user and their AI agents have been working on. Use when starting a session, when the user mentions recent activity, when the user alludes to what they were doing or looking at, or picking up where they left off. Also use when the conversation feels like a topic…

autographical/claude-code-plugins · 75 tokens

user-profile

Use to create or update the user's anchor profile — a single private file (/bettersense-work-reflections/profile.md) that captures who the user is, what they do, what context other skills need to know about them. Read automatically by other skills in the bundle when present, so the user doesn't re-explain themselves…

shwetank/bettersense · 131 tokens

career-retro

Use for a periodic (quarterly / annual) career retrospective across the ENTIRE bettersense memory — producing a longitudinal self-assessment with cited growth deltas since the last retro and the honest gaps to work on next. Trigger phrases include "run my career retro", "where am I in my career", "annual…

shwetank/bettersense · 166 tokens

doctor

Use to health-check the user's bettersense memory directory — validate the file layout, catch problems before they cost data, and set up backups. Trigger phrases include "run bettersense doctor", "check my reflection files", "is my bettersense data okay", "something seems off with my stakeholder files", "back up my…

shwetank/bettersense · 0 tokens

capture

Use to log something from the current conversation into the user's bettersense memory without re-typing it — a decision that just got made, a win that surfaced mid-discussion, an observation about a stakeholder, a self-insight. Trigger phrases include "log this", "capture this", "save that decision", "add that to my…

shwetank/bettersense · 0 tokens