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.
curl -O https://raw.githubusercontent.com/thomas-powers-jr/cadence/main/.claude/commands/handoff.mdgit clone --depth 1 https://github.com/thomas-powers-jr/cadenceWrote 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.
[](https://agentmods.dev/commands/thomas-powers-jr/cadence/handoff)<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>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 5.1 | $0.00029 | $0.02146 |
| Opus 5 | $0.00015 | $0.01073 |
| Sonnet 5 | $0.00006 | $0.00429 |
| Haiku 4.5 | $0.00003 | $0.00215 |
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.
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
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.
- 7d ago First seen · 112 lines · 29 tokens per session scan A e6ffd4ccbfa0
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.
Other commands, from other repositories
undo-commit
Soft-undo the last commit. Restores its changes as staged, leaves working tree intact. Refuses if HEAD is already pushed to a tracked remote.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.
afcl
Close feature [agent] [--adopt] - merges branch, cleans up, optionally adopts from losers (shortcut for feature-close).
afsr
Review feature spec - improve the spec itself before implementation (shortcut for feature-spec-review).