A handoff tool for carrying selected context from one coding session into the next before clearing the session.

Use it with Session Watcher to choose what to keep or discard, create a redacted structured summary, and receive a token for loading the handoff later.

It reduces repeated reading by preserving only the relevant files, symbols, skills, summary, and next task.

sw-handoff — Skill for Claude Code and Codex by nomadop: A handoff tool for carrying selected context from one…

Install

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.

agentmods

npx agentmods add skills/nomadop/session-watcher/sw-handoff

Any agent

npx skills add nomadop/session-watcher --skill sw-handoff

Clone the repo

git clone --depth 1 https://github.com/nomadop/session-watcher

Made for: Claude Code, Codex.

Or install session-watcher, the plugin that ships this one along with the rest of its 3 skills, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nomadop/session-watcher/sw-handoff.svg)](https://agentmods.dev/skills/nomadop/session-watcher/sw-handoff)

Your own site

<a href="https://agentmods.dev/skills/nomadop/session-watcher/sw-handoff"><img src="https://agentmods.dev/badge/skills/nomadop/session-watcher/sw-handoff.svg" alt="Measured on agentmods" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 629 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00050	$0.00629
Opus 5	$0.00025	$0.00315
Sonnet 5	$0.00010	$0.00126
Haiku 4.5	$0.00005	$0.00063

Measured 5d ago against content hash ff1927d8f072, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sw-handoff scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Fallback (MCP unavailable): resolve the server URL from session-start additionalContext (`Session Watcher server: http://...`) and use `curl -s -X POST '<url>/api/handoff/prepare'` with the same JSON body.

skills/sw-handoff/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Watcher Handoff

Prepare a handoff package so the next session can resume with minimal re-reading.

Steps

Fetch bucket data via MCP get_bucket_summary tool.

If metrics.br < 0.05 AND few turns: note "Context is still light — handoff may not be necessary yet, but proceeding as requested."
Select paths to keep — for each path in the bucket summary:
- Decide keep or discard based on relevance to next_task
- If the path has userOverride, apply the user's decision (keep/discard)
- If the path has activeSymbols, select which symbols to keep (these are verified — no guessing needed)
- Pass kept symbol names in paths_to_keep[].symbols
Select skills — skills_to_keep: only skills actively guiding the workflow or required by next_task. Skip one-shot completed skills. Never include sw-load — it drives the load flow itself and is always invoked automatically. If the user's keep: list includes skill names, use those directly.
Write the summary you MUST following SUMMARY.md exactly. Redact secrets as [REDACTED]
Prepare via MCP prepare_handoff tool with:
- paths_to_keep: array from step 2
- skills_to_keep: array from step 3
- summary: from step 4
- next_task: what comes next. Default: if the user doesn't specify, infer from the current conversation — continue the work in progress (the task being actively worked on, not a generic description).
- observed_segment: segment value from step 1
Check resolved_paths in the response — if the server picked wrong, re-issue with the absolute path.

Update in place: to revise an existing handoff (fix paths, update summary), pass load_token of the existing handoff. The server overwrites that record instead of creating a new one.

Fallback (MCP unavailable): resolve the server URL from session-start additionalContext (Session Watcher server: http://...) and use curl -s -X POST '<url>/api/handoff/prepare' with the same JSON body.

Read the full file on GitHub · 45 lines

Files

What ships with it

1 file 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.

SUMMARY.md 1.5 KB

Changes

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 · 45 lines · 50 tokens per session scan A ff1927d8f072

Subscribe to this mod's changes

sw-handoff is a skill published in the GitHub repository nomadop/session-watcher (3 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 629 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Cost Optimization Memory and context coding-agents dashboard developer-tools eoq mcp-server

context-efficient-coding

Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…

divyanshu-iitian/ContextFlux · 72 tokens

git-ai-search

Search and restore AI conversation context from git history.

git-ai-project/git-ai · 13 tokens

memory-audit-pattern-extraction

模式提取与失效解药分析。当发现多条记忆在讲同一个教训，或发现自己在一而再再而三地犯同样的错误时使用。.

Dataojitori/nocturne_memory · 48 tokens

brain-ingest

The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.

mindmuxai/brain.md · 48 tokens

memorix-sessions

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.

AVIDS2/memorix · 31 tokens

frontmcp-extensibility

Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…

agentfront/frontmcp · 124 tokens

sw-handoff