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/OXI-717/ai-native-toolkitWrote 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/oxi-717/ai-native-toolkit/handoff)<a href="https://agentmods.dev/commands/oxi-717/ai-native-toolkit/handoff"><img src="https://agentmods.dev/badge/commands/oxi-717/ai-native-toolkit/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/oxi-717/ai-native-toolkit/handoff"><img src="https://agentmods.dev/badge/commands/oxi-717/ai-native-toolkit/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 | $0.00016 | $0.00696 |
| Opus 5.5 | $0.00006 | $0.00278 |
| Sonnet 5.5 | $0.00003 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compress the current session context into a handoff document. This preserves critical information before compaction.
Instructions
Review the ENTIRE current conversation and create a compressed handoff document.
What to Extract
- Goal — what user is trying to accomplish (1-2 lines)
- Files Modified — every file path touched, with what changed
- Decisions Made — architectural choices, rejected alternatives, reasons
- Key Context — project structure, conventions, constraints discovered
- Current State — what is done, what remains
- Errors/Solutions — issues encountered and how resolved
- Dependencies — external tools, APIs, configs involved
Compression Rules (Heavy Density, 60-75% reduction)
- Imperative mood, present tense, active voice
- 3-7 words per statement
- Bullets over paragraphs
key: valuefor named properties- Zero redundancy — state each fact once
- Preserve ALL: identifiers, file paths, values, decisions, causal relationships
- Use
→for flows,|for alternatives,?:for conditions
Output Format
Write the durable copy to ~/.claude/handoff/<project-hash>/<session-id>.md, where
project-hash is cwd with / replaced by -. If no session id is available, use
manual-<UTC timestamp>.md. Also copy the same content to HANDOFF.md as the
project-wide convenience pointer to the latest save:
# Context Handoff
- session: [session id if available]
- cwd: [working directory]
- branch: [git branch]
- saved: [ISO timestamp]
- method: manual
## Goal
[1-2 lines, compressed]
## Files Modified
- path/to/file — what changed
- ...
## Decisions
- Chose X over Y — reason
- ...
## Key Context
- [compressed bullets of critical information]
## Current State
- Done: [completed items]
- Remaining: [pending items]
## Errors Resolved
- issue → solution
- ...
Steps
- Run
mkdir -p ~/.claude/handoff/$(pwd | sed 's|/|-|g') - Analyze current conversation context
- Compress using rules above
- Write
<session-id>.md(ormanual-<UTC timestamp>.md), then copy it to HANDOFF.md - Write HANDOFF.meta.json:
{"session_id":"...","timestamp":"...","cwd":"...","method":"manual"} - MANDATORY: Confirm to user with this exact format:
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.
- 1mo ago Changed · +3 lines 12772484a8c2
- 1mo ago First seen · 87 lines · 16 tokens per session scan A 79dc54a710d0
handoff is a command published in the GitHub repository OXI-717/ai-native-toolkit (9 stars, last pushed 13d ago), licensed MIT. It adds 16 tokens to every session and 696 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).