cadence: Command for Claude Code

.claude/commands/handoff.md

handoff is a command for Claude Code from thomas-powers-jr/cadence. It costs 29 tokens per session (2,146 once invoked), scanned A, original, MIT.

An end-of-session command that records the current work in a handoff document, then commits and pushes it so another coding agent can continue.

In plain words
What is it for?
Use it to reconcile notes and documentation, describe the repository's true state, and prepare the current branch for another agent to resume.
Why use it?
It reduces the risk of losing context or claiming work that was not actually completed when a session ends.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

This is thomas-powers-jr/cadence's own configuration. It tells Claude Code how to work on cadence itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cadence configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node packages/core/dist/cli/index.js progress # or: node packages/core/bin/cadence.cjs progress.

Reuse

Borrowing it

Nothing to install: this file belongs to thomas-powers-jr/cadence. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/thomas-powers-jr/cadence/main/.claude/commands/handoff.md
Clone the repo
git clone --depth 1 https://github.com/thomas-powers-jr/cadence

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 handoff

README.md
[![agentmods](https://agentmods.dev/badge/commands/thomas-powers-jr/cadence/handoff.svg)](https://agentmods.dev/commands/thomas-powers-jr/cadence/handoff)
Your own site
<a href="https://agentmods.dev/commands/thomas-powers-jr/cadence/handoff"><img src="https://agentmods.dev/badge/commands/thomas-powers-jr/cadence/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,146 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 $0.00029 $0.02146
Opus 5 $0.00015 $0.01073
Sonnet 5 $0.00006 $0.00429
Haiku 4.5 $0.00003 $0.00215

Measured 7d ago against content hash e6ffd4ccbfa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 7d 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.

.claude/commands/handoff.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/handoff — session handoff

You are closing out a work session on CADENCE (and, when on praxis-intelligence-ledger, the Praxis layer). Produce a clean, truthful handoff so a fresh LLM session can resume with zero context loss.

$ARGUMENTS (optional) is a short context label for the handoff filename / title (e.g. v1.2-slice7, bugfix-F2). If empty, derive one from the branch + the dominant work this session.

Hard rules:

  • Truth over tidiness. Document only what actually happened and what is actually true in the repo right now. Never invent progress, test results, or "next steps" that weren't established. If something is uncertain, say so explicitly in the handoff.
  • No silent scope creep. Do not refactor, "fix while I'm here", merge the PR, undraft a PR, or push tags. Tag pushes and PR merges require separate explicit user approval — out of scope for /handoff.
  • Push is in scope for this command (the user invoked /handoff, which explicitly requests commit + push of the current branch). But the pre-push hook runs the full gate — if it fails, stop and report; do not --no-verify.

Work the steps in order. Use a TodoWrite list to track them.


Step 0 — Capture ground truth

Run and read, do not skip:

git status --short --branch
git branch --show-current
git log --oneline -8
git diff --stat
node packages/core/dist/cli/index.js progress   # or: node packages/core/bin/cadence.cjs progress

If on praxis-intelligence-ledger, also: git log origin/praxis-intelligence-ledger..HEAD --oneline and note draft PR #9 status (do not change it).

Form a precise mental model: what landed this session, what's uncommitted, what's in-flight (loop position / active phase / active slice), what's blocked, what's next. Everything downstream must match this.

Step 1 — Run the gate (honest status)

The handoff must record real gate state, not assumed. Run the full done-bar:

pnpm turbo run lint typecheck test build

Read the full file on GitHub · 112 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. 7d ago First seen · 112 lines · 29 tokens per session scan A e6ffd4ccbfa0

Subscribe to this mod's changes

handoff is a command published in the GitHub repository thomas-powers-jr/cadence (2 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 2,146 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 2026-08-31.