Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add TusharKarkera22/claude-loadout/plugin install claude-loadoutWrote 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/tusharkarkera22/claude-loadout/handoff-resume)<a href="https://agentmods.dev/commands/tusharkarkera22/claude-loadout/handoff-resume"><img src="https://agentmods.dev/badge/commands/tusharkarkera22/claude-loadout/handoff-resume/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.
<a href="https://agentmods.dev/commands/tusharkarkera22/claude-loadout/handoff-resume"><img src="https://agentmods.dev/badge/commands/tusharkarkera22/claude-loadout/handoff-resume.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.00600 |
| Opus 5 | $0.00013 | $0.00300 |
| Sonnet 5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
handoff-resume 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 12d 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.
What it actually says
You are helping the user pick up an in-progress handoff from a teammate. Patch application happens only after the user explicitly says yes.
The user passed: $ARGUMENTS
Step 1 — Fetch the bundle to a stable local path. Pick the first positional token from $ARGUMENTS as the source. If it looks like a local directory containing a handoff.json, use it directly. Otherwise clone it into a temp dir at ~/.claude-loadout/_handoff-staging/<short-id>/ (create the parent dir if missing). Use git clone --depth 1 for a Git URL; expand owner/repo shorthand to https://github.com/owner/repo.git.
Print the local bundle path you ended up with so the user can see it.
Step 2 — Run resume in review mode (no apply). Forward the remaining flags from $ARGUMENTS (everything after the source) and add --no-apply. Use the local bundle path you just resolved as the source argument:
node "${CLAUDE_PLUGIN_ROOT}/bin/cli.cjs" handoff resume <local-bundle-path> --no-apply <remaining-flags>
The CLI validates the manifest, optionally checks out the author's branch, and prints a git apply --stat diff stat. Capture both stdout and stderr — the diff stat lands on stderr.
Step 3 — Surface the summary + scope. Read <local-bundle-path>/handoff.md and show it to the user. Then present the diff stat the CLI emitted. Together these answer: what was the teammate doing, and how big is the patch I'm about to take?
Step 4 — Ask before applying. Ask the user verbatim: "Apply this patch to your working tree? (y/N)". Do not apply unless they answer yes. If they say no or hesitate, stop here and offer to discuss the changes first.
Step 5 — Apply on confirmation. If the user confirms, run the same command without --no-apply and with --yes (since the CLI is non-interactive in this context):
node "${CLAUDE_PLUGIN_ROOT}/bin/cli.cjs" handoff resume <local-bundle-path> --yes <remaining-flags>
Surface the CLI's output (branch switched, patch applied), then propose the first concrete next task from the summary's "What's pending" / "What I'd do next" sections. Confirm with the user before starting work.
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.
- 12d ago First seen · 33 lines · 26 tokens per session scan A de0cce57c5c2
handoff-resume is a command published in the GitHub repository TusharKarkera22/claude-loadout (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 600 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
mr-description-creator
Generate and apply MR/PR description directly via gh or glab CLI (project).
justone-publish
Publish a completed JustOne build — create a public GitHub repo, push, and register on the gallery.
icpg-bootstrap
Infer ReasonNodes from existing git commit history. One-time setup for existing codebases.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.