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/jobshwang/skills/handoffgit clone --depth 1 https://github.com/JobsHwang/skillsWrote 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/jobshwang/skills/handoff)<a href="https://agentmods.dev/commands/jobshwang/skills/handoff"><img src="https://agentmods.dev/badge/commands/jobshwang/skills/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 | $0.00038 | $0.00305 |
| Opus 5 | $0.00019 | $0.00152 |
| Sonnet 5 | $0.00008 | $0.00061 |
| Haiku 4.5 | $0.00004 | $0.00030 |
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 5d 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
The user explicitly invoked /handoff.
Invocation arguments: $ARGUMENTS
Handoff
Create one concise handoff that lets a fresh agent continue without reconstructing the conversation.
- Treat invocation arguments or accompanying user text as the next agent's objective. If none is provided, infer the immediate next objective from the conversation.
- Inspect only the repository state needed to distinguish completed, pending, and unverified work.
- Write the handoff to the operating system's temporary directory, never into the workspace. Use a short unique filename ending in
.md. - Include:
- next objective;
- current state;
- confirmed decisions and constraints;
- artifacts to read first, using absolute paths or stable URLs;
- open work, risks, and unverified claims;
- suggested explicit Skills, only when they materially help the next step.
- Reference existing Specs, PRDs, ADRs, commits, and diffs instead of duplicating their contents.
- Do not invent progress, decisions, test results, or repository state. Redact secrets and sensitive personal information.
- Do not implement, review, commit, or modify workspace files while handing off.
- Return the absolute handoff path and one sentence describing what the next agent should do.
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.
- 5d ago First seen · 27 lines · 38 tokens per session scan A e96704c7b02d
handoff is a command published in the GitHub repository JobsHwang/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 305 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.