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.
git 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/commands/povvo/claudikins-automatic-context-manager/manual-handoff)<a href="https://agentmods.dev/commands/povvo/claudikins-automatic-context-manager/manual-handoff"><img src="https://agentmods.dev/badge/commands/povvo/claudikins-automatic-context-manager/manual-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/commands/povvo/claudikins-automatic-context-manager/manual-handoff"><img src="https://agentmods.dev/badge/commands/povvo/claudikins-automatic-context-manager/manual-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 | $0.00027 | $0.00201 |
| Opus 5 | $0.00014 | $0.00101 |
| Sonnet 5 | $0.00005 | $0.00040 |
| Haiku 4.5 | $0.00003 | $0.00020 |
Grade A, and why
claudikins-automatic-context-manager:manual-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
claudikins-automatic-context-manager:manual-handoff Command
You are manually triggering a context handoff, bypassing the automatic 60% threshold.
Workflow
- Create the threshold flag file
- Notify user that handoff will trigger on next prompt
Execute
Run this Bash command to create the flag:
SESSION_ID="${CLAUDE_SESSION_ID:-manual}"
echo "manual" > "/tmp/acm-threshold-${SESSION_ID}"
echo "Handoff trigger set. Send any message to see the handoff prompt."
What Happens Next
After running, send any message and the handoff popup will appear, allowing you to:
- Generate a summary of the current session
- Continue in a fresh context with the summary loaded
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.
- 10d ago First seen · 32 lines · 27 tokens per session scan A 96a11bb8840b
claudikins-automatic-context-manager:manual-handoff is a command published in the GitHub repository povvo/claudikins-automatic-context-manager (14 stars, last pushed 7mo ago), licensed MIT. It adds 27 tokens to every session and 201 once invoked, about $0.0001 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 commands, from other repositories
checkpoint
Full memory flush — refresh state.md, append to activity log, route any new decisions/insights, then commit and push.
handoff
Fast session handover — capture current state and write a resume command for the next session. Use when context is filling up or you need to switch tasks.
wrap-up
End-of-session protocol — capture decisions, constraints, learnings, and next-session task; create a session snapshot before context is lost.
retrieve
Full-text search persistent memory (BM25) and present results grouped by category — decisions, constraints, learnings, tasks.
unwrap
You are resuming a Claude Code session. Execute all steps below in order — no confirmation needed.
create
Capture current session context to docs/handoff/HANDOFF.md.