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-sprint)<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-sprint"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-sprint/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-sprint"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-sprint.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 | $0.04484 |
| Opus 5.5 | $0.00000 | $0.01794 |
| Sonnet 5.5 | $0.00000 | $0.00897 |
| Haiku 4.5 | $0.00000 | $0.00448 |
Grade A, and why
sdlc-sprint 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc-sprint — Slate, Ready, and Close a Sprint
Run a two-week sprint as a commitment window over the backlog order: create the sprint record,
slate a count of specs by risk-tier mix, watch the slate's readiness every day, mark the sprint
ready once every slated spec clears the Definition of Ready and its Engineering and Data verdicts,
and close it with kept / carried / dropped — each carry or drop by a named human, with a reason. The
layer is additive and advisory: it never gates, is never gated, never moves a phase, and never writes
state.yaml. Works inside an SDLC project or standalone against any repo with a specs/ directory.
The command owns sprint.py; the user never calls it directly. The pure rules (mix, ready rule, build
order, forbidden metrics) live in references/sprint-model.md; the record template is
templates/phases/build/sprint.md.
When it runs
/sdlc-sprint is not one moment. Different verbs belong to different points in the two-week rhythm:
| Moment | Verbs | Who | Companion |
|---|---|---|---|
| Setting up the next sprint — the current sprint's last week, at the Mon/Wed/Fri review | new, slate, unslate |
Product proposes and confirms the slate | /sdlc-refine --sprint drives the slated specs to READY and records the Eng/Data verdicts |
| Sprint planning meeting — day 0 | ready (writes the planning page); plan re-renders it on demand |
a named human readies it; the team walks the page | the page is the meeting's agenda and record |
| Every day — the flow check | status (default) |
anyone | /sdlc-refine (no arguments) for the refinement agenda |
| Whenever work changes hands | handoff, ack |
the recorder and the recipient | — |
| Last day — sprint review and Retro+ | close (writes the review page) |
a named human confirms every carry and drop | /sdlc-retro for the cross-sprint patterns |
Instructions
- Resolve mode and repo root:
- Workflow mode (default): look for
.sdlc/state.yaml; pass--state .sdlc/state.yamlto every call. The repo root is the directory containing.sdlc/; specs are<repo>/specs/*.md. - Standalone mode (
--repo <path>, or no.sdlc/state.yamlfound): pass--repo <path>. The sprint record and ledger are created under<repo>/.sdlc/sprints/and<repo>/.sdlc/metrics/sprint-log.jsonl; the output notes the missing engagement context (standalone mode — no .sdlc/state.yaml; engagement context not shown). A bare.sdlc/directory withoutstate.yamlis still standalone. - Every example below shows
--state .sdlc/state.yaml; substitute--repo <path>in standalone mode. The two flags are mutually exclusive.
- Workflow mode (default): look for
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 First seen · 235 lines · 0 tokens per session scan A 1d984c3c9785
sdlc-sprint 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 4,484 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 2026-10-08.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.