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 skills/codagent-ai/agent-skills/handoffnpx skills add Codagent-AI/agent-skills --skill handoffgit clone --depth 1 https://github.com/Codagent-AI/agent-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/skills/codagent-ai/agent-skills/handoff)<a href="https://agentmods.dev/skills/codagent-ai/agent-skills/handoff"><img src="https://agentmods.dev/badge/skills/codagent-ai/agent-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 | $0.00081 | $0.00706 |
| Opus 5 | $0.00041 | $0.00353 |
| Sonnet 5 | $0.00016 | $0.00141 |
| Haiku 4.5 | $0.00008 | $0.00071 |
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 4d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Write a focused summary of a specific aspect of the current conversation so a fresh agent can pick up where this session left off.
This is NOT a full conversation summary. The user's prompt tells you which aspect to capture. If the aspect is unclear, ask for clarification before proceeding.
What to capture
For the aspect the user specified, write:
- Objective — What the user is trying to accomplish (the goal, not the history).
- Current state — Where things stand right now. What's done, what's in progress, what's blocked.
- Key decisions — Decisions made during this session that the next agent must honor, with brief rationale.
- Open questions — Unresolved issues, trade-offs still being weighed, or things the user hasn't decided yet.
- Next steps — Concrete actions the resuming agent should take first.
- Relevant files — Paths to files that were created, modified, or are central to the work.
Omit any section that has nothing meaningful to say. Keep it tight — the resuming agent needs signal, not narration.
Output
Write the summary to handoff.md.
Determining the output location:
- If the user specified a path in their prompt, use it.
- If a project configuration (e.g., AGENTS.md, openspec config, or similar conventions) specifies a change directory, write there.
- Otherwise, determine the relevant change slug from context (the change being worked on, or a kebab-case slug from the topic) and write to
~/.agent-skills/changes/<slug>/handoff.md.
Do not ask the user to confirm the location. Just write to the resolved path.
Template
# Handoff: <aspect being handed off>
## Objective
<!-- What the user is trying to accomplish -->
## Current State
<!-- Where things stand: done, in progress, blocked -->
## Key Decisions
<!-- Decisions made this session that the next agent must honor -->
- **<decision>** — <rationale>
## Open Questions
<!-- Unresolved issues or trade-offs -->
## Next Steps
<!-- Concrete first actions for the resuming agent -->
## Relevant Files
<!-- Paths to files central to this work -->
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.
- 4d ago First seen · 79 lines · 81 tokens per session scan A 955f2ce4104d
handoff is a skill published in the GitHub repository Codagent-AI/agent-skills (30 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 706 once invoked, about $0.0004 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 skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…