acm-handoff

acm-handoff is a skill for Claude Code from povvo/claudikins-automatic-context-manager. It costs 43 tokens per session (506 once invoked), scanned A, original, MIT.

A handoff tool for restoring work from an earlier coding-agent session that ran out of context. It reads saved state and a Markdown summary from the repository.

In plain words
What is it for?
It helps resume interrupted sessions and restore their task list and working state.
Why use it?
It brings back the previous objective, unfinished tasks, changed files, branch details, and other context so work can continue accurately.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the TodoWrite tool.

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

Good fit It helps resume interrupted sessions and restore their task list and working state.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/povvo/claudikins-automatic-context-manager/acm-handoff"><img src="https://agentmods.dev/badge/skills/povvo/claudikins-automatic-context-manager/acm-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00043 $0.00506
Opus 5 $0.00022 $0.00253
Sonnet 5 $0.00009 $0.00101
Haiku 4.5 $0.00004 $0.00051

Measured 11d ago against content hash 668a980fc44f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

acm-handoff 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 11d 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.

skills/acm-handoff/SKILL.md · 65 lines

What it actually says

Context Handoff

This skill loads handoff content from a previous session that reached the context threshold.

Instructions

When this skill is invoked:

  1. Check for structured state at .claude/claudikins-acm/handoff-state.json
  2. Read the handoff markdown at .claude/claudikins-acm/handoff.md
  3. Present both to understand what was being worked on
  4. Restore todos if active todos exist in the state
  5. Continue the work from where it was left off

File Locations

File Purpose
.claude/claudikins-acm/handoff-state.json Structured state (preferred)
.claude/claudikins-acm/handoff.md Human-readable summary

Reading the State

The structured state JSON contains:

  • context.current_objective - What was being worked on
  • context.active_todos - Pending/in-progress todos to restore
  • context.key_files_modified - Recently changed files
  • git.branch - Git branch at handoff time
  • git.modified_files - Uncommitted changes

After Reading

  1. Restore todos using TodoWrite if active_todos has entries
  2. Summarise the previous session's state for the user
  3. Ask if they want to continue from where they left off
  4. Clean up the handoff files after successful restoration

Cleanup

After successfully restoring context, offer to clean up:

rm -f .claude/claudikins-acm/handoff-state.json
rm -f .claude/claudikins-acm/handoff.md

If No Handoff Exists

If neither file exists, inform the user:

  • No handoff is currently active
  • A handoff is created when context usage hits the threshold (default 60%)
  • They can configure the threshold via /acm:config

Claudikins Automatic Context Manager To configure settings, use: /acm:config

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. 11d ago First seen · 65 lines · 43 tokens per session scan A 668a980fc44f

Subscribe to this mod's changes

acm-handoff is a skill published in the GitHub repository povvo/claudikins-automatic-context-manager (14 stars, last pushed 7mo ago), licensed MIT. It adds 43 tokens to every session and 506 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 2026-08-30.

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

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

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