paul:pause

A command that prepares a project handoff before a work session ends, including the current state, completed work, next action, and resume instructions.

In plain words
What is it for?
Use it when pausing development, handing work to another session or contributor, or approaching a context limit.
Why use it?
It preserves enough context for work to continue after a break or context switch. It also updates the project state and can optionally create a work-in-progress commit.

Command

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 commands/christopherkahler/paul/pause
Clone the repo
git clone --depth 1 https://github.com/ChristopherKahler/paul
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 286 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00286
Opus 5 $0.00007 $0.00143
Sonnet 5 $0.00003 $0.00057
Haiku 4.5 $0.00001 $0.00029

Measured 2d ago against content hash 7135a3eade20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paul:pause 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 2d 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.

src/commands/pause.md · 45 lines

What it actually says

When to use: Before ending a session, switching context, or when context limit is approaching.

<execution_context> @~/.claude/paul-framework/workflows/pause-work.md </execution_context>

@.paul/STATE.md @.paul/PROJECT.md

The workflow handles:

  1. Detecting current position
  2. Gathering session context (ask user if needed)
  3. Creating HANDOFF-{date}.md with populated content
  4. Updating STATE.md session continuity
  5. Optional WIP commit
  6. Confirmation display

If [reason] argument provided, include it in handoff status.

<success_criteria>

  • HANDOFF.md created with complete context (no placeholders)
  • STATE.md updated with session continuity
  • Next action is clear and actionable
  • Resume instructions provided </success_criteria>
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. 2d ago First seen · 45 lines · 14 tokens per session scan A 7135a3eade20

Subscribe to this mod's changes

paul:pause is a command published in the GitHub repository ChristopherKahler/paul (1,212 stars, last pushed 11d ago), licensed MIT. It adds 14 tokens to every session and 286 once invoked, about $0.0001 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.