csm-handoff-writer

csm-handoff-writer is an agent for Claude Code from NovasPlace/CSM. It costs 33 tokens per session (232 once invoked), scanned A, original, MIT.

A handoff agent that records the current work state so another session or agent can continue it. A handoff is a concise transfer note covering progress, changes, checks, risks, and the next action.

In plain words
What is it for?
Saving hard-to-recreate state in a checkpoint, recording a durable milestone, and writing a concrete handoff summary without storing secrets.
Why use it?
It reduces the effort needed to reconstruct work after stopping, context compression, or transferring responsibility.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cross-session-memory plugin — 2 skills, 12 commands, 3 agents shipped together

Good fit Saving hard-to-recreate state in a checkpoint, recording a durable milestone, and writing a concrete handoff summary without storing secrets.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/novasplace/csm/csm-handoff-writer
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.

Clone the repo
git clone --depth 1 https://github.com/NovasPlace/CSM

Made for: Claude Code.

Or install cross-session-memory, the plugin that ships this one along with the rest of its 2 skills, 12 commands, 3 agents.

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.

agentmods badge for csm-handoff-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/novasplace/csm/csm-handoff-writer/github.svg)](https://agentmods.dev/agents/novasplace/csm/csm-handoff-writer)
Your own site
<a href="https://agentmods.dev/agents/novasplace/csm/csm-handoff-writer"><img src="https://agentmods.dev/badge/agents/novasplace/csm/csm-handoff-writer/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.

agentmods 80×15 button for csm-handoff-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/novasplace/csm/csm-handoff-writer"><img src="https://agentmods.dev/badge/agents/novasplace/csm/csm-handoff-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 232 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00232
Opus 5 $0.00016 $0.00116
Sonnet 5 $0.00007 $0.00046
Haiku 4.5 $0.00003 $0.00023

Measured 10d ago against content hash 0971bb1cbf68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

csm-handoff-writer 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.

plugins/cross-session-memory/agents/csm-handoff-writer.md · 15 lines

What it actually says

You are the CSM Handoff Writer. You make transitions safe and cheap to resume.

Procedure:

  1. Resolve projectRoot to the current workspace root.
  2. Inspect csm_context_pressure when a snapshot is available to judge urgency.
  3. If the current state would be expensive to reconstruct, create_checkpoint (check list_checkpoints to avoid redundant ones).
  4. Record the final durable milestone with bridge_sync_turn, then call bridge_handoff_summary.
  5. Make the handoff concrete: outcome, files changed, verification performed, open risks, and the next action. Never persist secrets, credentials, or unnecessary sensitive content.
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.

  1. 10d ago First seen · 15 lines · 33 tokens per session scan A 0971bb1cbf68

Subscribe to this mod's changes

csm-handoff-writer is an agent published in the GitHub repository NovasPlace/CSM (42 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 232 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 2026-08-30.

Related

Other agents, from other repositories

session-retrospective

Cross-session pattern analyzer. Reads the last N session logs and produces a dated retrospective artifact with root cause hypotheses, deferred task tracking, behavioral drift checks, and verifiable recommendations with confidence levels and testable predictions. Each recommendation gets a unique ID tracked across…

sliamh11/Deus · 0 tokens

dx-engineer

Use this agent when developer experience needs to be evaluated, designed, or improved. This includes: CLI UX audits, SDK API design review, onboarding flow optimization, error message quality, documentation architecture, configuration UX, terminal output formatting, installation experience, example code quality, and…

nxtg-ai/forge-plugin · 298 tokens

progressive_disclosure_agent

A review agent for keeping a skill’s instructions short, focused, and loaded in the right order. It checks whether background material, code, and templates should be moved into separate reference files, scripts, or assets.

BingHanOfUESTC/open_agent_team · 31 tokens

chief-of-staff

Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.

Fmarzochi/EGC · 61 tokens

chief-of-staff

Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.

sifxprime/kodelyth-ecc · 61 tokens

evidence_ingestion_agent

An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.

BingHanOfUESTC/open_agent_team · 30 tokens