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 skills add buddyh/agent-skills --skill claude-session-handoffgit clone --depth 1 https://github.com/buddyh/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/buddyh/agent-skills/claude-session-handoff)<a href="https://agentmods.dev/skills/buddyh/agent-skills/claude-session-handoff"><img src="https://agentmods.dev/badge/skills/buddyh/agent-skills/claude-session-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/skills/buddyh/agent-skills/claude-session-handoff"><img src="https://agentmods.dev/badge/skills/buddyh/agent-skills/claude-session-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 | $0.00094 | $0.00971 |
| Opus 5 | $0.00047 | $0.00485 |
| Sonnet 5 | $0.00019 | $0.00194 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
claude-session-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Session Handoff
Recover the state of a prior Claude Code session, then confirm what actually exists in the current workspace before continuing.
Workflow
1. Find the right session
Default to the current project path unless the user gives a specific JSONL file.
For the common handoff case, do not search every Claude transcript first. Bias toward the current repo, the most recent top-level session, and recent activity.
Run the helper script:
python3 scripts/claude_session_handoff.py --project-path "$PWD"
Useful variants:
python3 scripts/claude_session_handoff.py --project-path "$PWD" --list
python3 scripts/claude_session_handoff.py --project-path "$PWD" --date YYYY-MM-DD
python3 scripts/claude_session_handoff.py --session /path/to/session.jsonl
python3 scripts/claude_session_handoff.py --recent 10
python3 scripts/claude_session_handoff.py --project-path "$PWD" --date YYYY-MM-DD --contains "anchor phrase" --from-match
Use these defaults:
- Start with the current repo and the newest top-level session.
- If the user implies "today", resolve that to the exact local date and pass
--date YYYY-MM-DD. - Read the last meaningful turns first. Do not read the entire transcript by default.
- Use
--listwhen multiple Claude sessions exist for the same project and you want the candidate set before choosing one. - Use
--recentwhen the repo moved and the storedcwdno longer matches the current path.
2. Read only the meaningful turns
The helper script already filters the noisy parts, but keep these rules in mind:
- Ignore
subagents/files unless the user explicitly wants delegated-session context. - Ignore local-command pseudo-messages such as
<local-command-caveat>,<command-name>, and<local-command-stdout>. - Ignore assistant messages that are only
[thinking]or other non-user-visible placeholders. - Treat images as context markers, not text that needs verbatim transcription.
Default to the most recent meaningful turns only. Large transcripts should be narrowed before you read deeply.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 102 lines · 94 tokens per session scan A d3f25b0fd696
claude-session-handoff is a skill published in the GitHub repository buddyh/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 971 once invoked, about $0.0005 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 skills, from other repositories
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
comet-memory
A review step for deciding whether information should become durable personal memory. It can keep, update, forget, or skip memory candidates based on bounded evidence.
recall-memory
Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.
agent-expert-creation
Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…