putdown

putdown is a skill for Claude Code from cabaynes/charles-claude-skills. It costs 98 tokens per session (2,817 once invoked), scanned A, original, MIT.

A session handoff tool that records the current coding work so a new assistant session can continue it. It can also save lasting notes, update project guidance files, and commit and push the session's changes.

In plain words
What is it for?
Use it before stepping away, ending a session, or starting with a fresh context. It helps preserve decisions, current progress, remaining work, and repository changes.
Why use it?
It prevents important context from being lost when a conversation ends or its context is cleared. The next session can use the handoff instead of reconstructing the work from scratch.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the TodoWrite tool.

Good fit Use it before stepping away, ending a session, or starting with a fresh context. It helps preserve decisions, current progress, remaining work, and repository changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cabaynes/charles-claude-skills/putdown
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.

Any agent
npx skills add cabaynes/charles-claude-skills --skill putdown
Clone the repo
git clone --depth 1 https://github.com/cabaynes/charles-claude-skills

Made for: Claude Code.

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 putdown

README.md
[![agentmods](https://agentmods.dev/badge/skills/cabaynes/charles-claude-skills/putdown/github.svg)](https://agentmods.dev/skills/cabaynes/charles-claude-skills/putdown)
Your own site
<a href="https://agentmods.dev/skills/cabaynes/charles-claude-skills/putdown"><img src="https://agentmods.dev/badge/skills/cabaynes/charles-claude-skills/putdown/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 putdown

Your own site · 80×15
<a href="https://agentmods.dev/skills/cabaynes/charles-claude-skills/putdown"><img src="https://agentmods.dev/badge/skills/cabaynes/charles-claude-skills/putdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,817 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 $0.00098 $0.02817
Opus 5 $0.00049 $0.01409
Sonnet 5 $0.00020 $0.00563
Haiku 4.5 $0.00010 $0.00282

Measured yesterday against content hash 882ae6ac164a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

putdown 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 yesterday.

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.

skills/session-continuity/putdown/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/putdown — Context handoff before clearing

The user is about to clear the context window and start fresh. Your job: capture everything a new agent would need so the next session loses no momentum.

Renamed from /checkpoint on 2026-06-12 (paired with /resume/pickup) because those names shadow Claude Code built-ins (/checkpoint aliases /rewind; /resume opens the conversation picker). On 2026-06-13 the handoff files also moved from .checkpoints/.putdowns/ to drop the old term entirely. If you ever see a stray .checkpoints/ folder, it predates the move — treat it as a putdown.

Step 0 — Announce what's about to run

If /takenotes is installed, a putdown is two operations, not one. Print this first so the user knows what's running and in what order:

/putdown runs two skills, in this order:
  1. /takenotes — harvest this session into memory, CLAUDE.md, and docs/
  2. /putdown   — write the handoff file, then commit and push everything

If /takenotes is not installed, skip the announcement. Either way this is an announcement, not a prompt — don't wait for confirmation, continue to Step 1.

Step 1 — Read current state (parallel)

Before writing anything, gather context. Run these in parallel:

  • pwd — where the session is rooted
  • git status and git log --oneline -10 — if it's a git repo (skip silently if not)
  • git diff --stat — what's changed, uncommitted
  • Read the project-level CLAUDE.md if one exists in the CWD
  • Read ~/.claude/projects/<project-slug>/memory/MEMORY.md to know which memory files exist
  • Check the current TodoWrite list state (if you have one in this session — recall from conversation, don't invent)
  • echo "$CLAUDE_CODE_ENTRYPOINT" — which surface this is. cli = terminal (standalone or VSCode's integrated terminal); anything else (or empty) = VSCode's visual-editor chat panel or another GUI surface. This decides the clear-context instructions in Step 5.

Also pull from your conversation memory:

  • What was the user actually trying to accomplish in this session?
  • What did you finish? What's half-done?
  • What file paths and line numbers are you in the middle of?
  • What did you try that didn't work, and why?
  • Any decisions made with non-obvious rationale?
  • Any errors, blockers, or open questions waiting on the user?

Read the full file on GitHub · 161 lines

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. yesterday Changed 882ae6ac164a
  2. 10d ago First seen · 161 lines · 98 tokens per session scan A 0e5b319b1ab0

Subscribe to this mod's changes

putdown is a skill published in the GitHub repository cabaynes/charles-claude-skills (1 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 2,817 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.

Related

Other skills, from other repositories

distill-habits

Review recent Claude Code conversations, distill the user's stable habits and preferences, persist them into a long-term habit ledger, and maintain a "My Habits" block in the global CLAUDE.md within a character budget. The more you use Claude Code, the more it knows you. Trigger manually with /distill-habits, or on a…

betayyang/claude-habit-distiller · 87 tokens

dream

A read-only review of project memories, notes, instructions, documents, and selected session records that produces a detailed report and a browser-viewable HTML report. It suggests ideas and insights but does not apply changes.

timoncool/dream-skill · 0 tokens

shipkit-work-memory

Log session progress and save resume state. Infers from conversation and git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.

stefan-stepzero/shipkit · 42 tokens

shipkit-claude-md

Update CLAUDE.md with learnings, preferences, or project context. Use when user says "update claude.md", "add to claude.md", or wants to persist something.

stefan-stepzero/shipkit · 45 tokens

init-project-memory

Use when the user says "init memory", "set up memory", "scaffold memory", "init project memory", or invokes /init-project-memory — creates the .claude/ session memory system in a new project.

jkm-4314/claude-code-skills · 48 tokens

session-update

Use when the user says "update session", "log progress", "checkpoint session", or invokes /session-update — especially before /clear or handoff.

jkm-4314/claude-code-skills · 33 tokens