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.
npx skills add povvo/claudikins-automatic-context-manager --skill acm-handoffgit clone --depth 1 https://github.com/povvo/claudikins-automatic-context-managerWrote 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.
[](https://agentmods.dev/skills/povvo/claudikins-automatic-context-manager/acm-handoff)<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.
<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>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 5.1 | $0.00043 | $0.00506 |
| Opus 5 | $0.00022 | $0.00253 |
| Sonnet 5 | $0.00009 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
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.
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:
- Check for structured state at
.claude/claudikins-acm/handoff-state.json - Read the handoff markdown at
.claude/claudikins-acm/handoff.md - Present both to understand what was being worked on
- Restore todos if active todos exist in the state
- 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 oncontext.active_todos- Pending/in-progress todos to restorecontext.key_files_modified- Recently changed filesgit.branch- Git branch at handoff timegit.modified_files- Uncommitted changes
After Reading
- Restore todos using TodoWrite if
active_todoshas entries - Summarise the previous session's state for the user
- Ask if they want to continue from where they left off
- 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
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.
- 11d ago First seen · 65 lines · 43 tokens per session scan A 668a980fc44f
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.
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.
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…
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…
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…
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…
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…