Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add OXI-717/ai-native-toolkit/plugin install context-handoffWrote 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/oxi-717/ai-native-toolkit/context-handoff)<a href="https://agentmods.dev/skills/oxi-717/ai-native-toolkit/context-handoff"><img src="https://agentmods.dev/badge/skills/oxi-717/ai-native-toolkit/context-handoff.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.02167 |
| Opus 5 | $0.00048 | $0.01084 |
| Sonnet 5 | $0.00019 | $0.00433 |
| Haiku 4.5 | $0.00010 | $0.00217 |
Grade D, and why
context-handoff scanned grade D with 2 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 7d 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
announces itself, a plausible wrong one silently sends the session down another task. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Check handoff: `cat ~/.claude/handoff/<project-hash>/HANDOFF.md` How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Handoff System
Preserve session context across /compact and /clear transitions.
Architecture
StatusLine (every turn)
│ shows CTX▼N% (remaining until auto-compact)
│
├─ User sees CTX▼<10% → runs /handoff (manual)
│ └─ Claude compresses context → HANDOFF.md
│ └─ Claude confirms: "Context saved. N sections, M bytes."
│ └─ User runs /compact
│
├─ Auto-compact fires (CTX▼~0%)
│ └─ PreCompact hook → auto-saves HANDOFF.md (safety net)
│
└─ After compact/clear
└─ SessionStart hook → injects HANDOFF.md as additionalContext
└─ Claude MUST follow "On Restore" protocol below
Three Mechanisms
| Mechanism | Trigger | Quality | Speed |
|---|---|---|---|
/handoff |
User types the command | High — Claude compresses | ~10s |
| PreCompact hook | Before /compact or auto-compact |
Medium — script extracts | <5s |
| SessionStart hook | After compact/clear | N/A — restores saved | <1s |
File Locations
| File | Purpose |
|---|---|
~/.claude/handoff/<project-hash>/HANDOFF.md |
Latest compressed context |
~/.claude/handoff/<project-hash>/HANDOFF.meta.json |
Metadata (session, timestamp, cwd) |
~/.claude/handoff/<project-hash>/<session-id>.md |
Per-session archive |
Project hash: cwd with / replaced by -. Example: /home/alex/work/repo -> -home-alex-work-repo
Handoff Format
# Context Handoff
- session: <id>
- cwd: <path>
- branch: <branch>
- saved: <timestamp>
- method: manual|auto
## Goal
## Files Modified
## Decisions
## Key Context
## Current State
## Errors Resolved
## Tool Usage
Workflow
- Work normally. StatusLine shows context % used.
- Context fills up (>70% in statusline)
- Options:
/handoff→ Claude compresses manually (recommended for critical work)/compact→ PreCompact hook auto-saves, then compaction runs- Auto-compact triggers → PreCompact hook fires automatically
- After compaction: SessionStart(compact) hook restores HANDOFF.md
- Claude follows "On Restore" protocol
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.
- 7d ago First seen · 272 lines · 97 tokens per session scan D 6690902af067
context-handoff is a skill published in the GitHub repository OXI-717/ai-native-toolkit (8 stars, last pushed 14d ago), licensed MIT. It adds 97 tokens to every session and 2,167 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 2 findings (tells the agent to send conversation or user data out, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".