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 MCKRUZ/claude-code-sdlc/plugin install claude-code-sdlcWrote 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/mckruz/claude-code-sdlc/sdlc-handoff)<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-handoff"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-handoff/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/mckruz/claude-code-sdlc/sdlc-handoff"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-handoff.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 | $0.00000 | $0.01365 |
| Opus 5.5 | $0.00000 | $0.00546 |
| Sonnet 5.5 | $0.00000 | $0.00273 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
sdlc-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 9d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc-handoff — Hand a Ready Spec to a Developer
Turn hand-off into one step: create the spec's branch, set its status/developer
frontmatter, assign the developer on the code host (and request a review from the spec's
checker, when one is set), and optionally start Claude Code on that branch in plan mode.
This is the Delegate beat's tool — the moment the loop's roles change hands.
Instructions
-
Resolve mode and repo root:
- Workflow mode (default): look for
.sdlc/state.yaml. The repo root is the directory containing.sdlc/. - Standalone mode (
--repo <path>, or no.sdlc/found): operate on the given repo.
- Workflow mode (default): look for
-
Confirm the spec and developer with the user if either wasn't given explicitly — do not guess who a spec should go to.
-
Run the hand-off (the command owns the script — the user never calls it directly):
uv run --project ${CLAUDE_PLUGIN_ROOT}/scripts ${CLAUDE_PLUGIN_ROOT}/scripts/handoff.py \ --repo <repo-root> --spec <repo-root>/specs/NNNN-name.md --developer @handleIn workflow mode pass
--state .sdlc/state.yamlinstead of--repo.The assignment step speaks to whichever code host the repository's
originremote is on — GitHub throughgh, Azure DevOps throughaz(with theazure-devopsextension). Detection is automatic; pass--host github|azure-devops|noneonly when the user asks to override it for this one run (nonetriesgh, as before). Do not add it to work around a CLI that is missing or signed out — the script already reports that as the assignment failure.- Refused — the script prints exactly what blocked it (not ready, unknown developer, developer is also the checker, team at its WIP limit) and changes nothing. Fix the named issue and re-run; do not work around a refusal by editing the spec's frontmatter by hand — the refusal exists because the script is about to act on that data.
- Team at its WIP limit — do not add
--over-limityourself. Tell the user the team is at capacity and ask whether to proceed anyway; only add--over-limit "<their reason>"on their explicit say-so, and use their own words as the reason (it is written into the commit message). - Already in flight — the script reports the developer already on file and changes nothing. This is not an error; report it plainly.
- On Azure DevOps,
assignment_errorwith the PR still opened — Azure DevOps names reviewers by sign-in identity, not by handle, so the checker becomes a required reviewer only when their roster entry in.sdlc/team.yamlcarries anemail:. Without one the draft PR opens with the gap written into its description and the script reports anassignment_error; the hand-off itself succeeded. Tell the user to add the checker'semail:(set_setting.py person @handle --email …) and request the review by hand this once. The developer is named in the PR description — Azure DevOps has no assignee.
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.
- 9d ago Changed · +19 lines 7be245353551
- 21d ago First seen · 71 lines · 0 tokens per session scan A 244da9ca8247
sdlc-handoff is a command published in the GitHub repository MCKRUZ/claude-code-sdlc (8 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,365 tokens. 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 2026-09-26.
Other commands, from other repositories
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
land
Resolve and squash merge one named, currently authorized pull request.
standup
Review my git commits from the past workday and generate a standup summary.
repo-architect
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.
sync
Synchronizes your local swarm state with the latest GitHub repository state, updating task statuses and detecting changes.
claim
Claims a GitHub issue for your swarm to work on, preventing conflicts with other swarms.