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 agentmods add commands/thepushkarp/handoff/resumegit clone --depth 1 https://github.com/thepushkarp/handoffWhat 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 | $0.00008 | $0.00480 |
| Opus 5 | $0.00004 | $0.00240 |
| Sonnet 5 | $0.00002 | $0.00096 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
resume 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 3d 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
Resume work from an existing handoff document at docs/handoff/HANDOFF.md.
Behavior
Default mode (no arguments): Display the handoff content and ask the user how they want to proceed.
Auto mode (--auto flag): Automatically inject the context and begin working on the next steps.
Steps
-
Check for Handoff File Read docs/handoff/HANDOFF.md if it exists.
-
Parse Most Recent Handoff The file may contain multiple handoff entries (appended with timestamps). Focus on the most recent handoff entry (the last
## Handoff: [TIMESTAMP]section in the file). -
Based on Mode:
If no arguments (default mode):
- Display a summary of the most recent handoff:
- When it was created
- Current task state
- Key decisions made
- Any blockers
- Next steps listed
- Ask the user: "How would you like to proceed? I can:
- Start working on the next steps
- Review the full handoff details first
- Do something else - please specify"
If
--autoflag provided:- Silently load the context
- Set up todos from the "Next Steps" section using TodoWrite
- Begin working on the first next step immediately
- Inform the user: "Resuming from handoff created at [TIMESTAMP]. Starting work on: [first next step]"
- Display a summary of the most recent handoff:
-
Handle Missing Handoff If docs/handoff/HANDOFF.md doesn't exist:
- Inform the user: "No handoff file found at docs/handoff/HANDOFF.md. Would you like to describe your current task so I can help you continue?"
Important Notes
- Pay attention to the "Critical Context" section - it contains gotchas and important info
- Respect any blockers mentioned - ask about their status before proceeding
- The "Key Decisions" section contains rationale that should guide continued work
- If multiple handoffs exist, you can offer to show history if user asks
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.
- 3d ago First seen · 53 lines · 8 tokens per session scan A 42f5946bd146
resume is a command published in the GitHub repository thepushkarp/handoff (9 stars, last pushed 6mo ago), licensed MIT. It adds 8 tokens to every session and 480 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
providers
Display Better Auth available authentication providers and their configuration.
thread
Manage conversation threads (create, switch, update, delete, show).
fe-start
前端开发 - 需输入任务描述 (如: /fe-start "开发组件").
verify
Verify any change surface against approved acceptance criteria and preserve evidence.
skill-inbox
Unified entry point for managing skill suggestions and browsing all installed skills. Provides two views: suggestions (default) and all skills.
eval-merge
Use the Read tool to load .skill-compass/{skill-name}/manifest.json. Verify.