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-refine)<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-refine"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-refine/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-refine"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-refine.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 | $0.05250 |
| Opus 5.5 | $0.00000 | $0.02100 |
| Sonnet 5.5 | $0.00000 | $0.01050 |
| Haiku 4.5 | $0.00000 | $0.00525 |
Grade A, and why
sdlc-refine 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc-refine — Refine the Sprint's Specs to Ready
Refine the specs slated into a sprint (or one spec) until each clears the Definition of Ready and its
independent Engineering and Data verdicts — the weekly Intent-triage ceremony made executable. With
no arguments it renders the refinement agenda for the Mon/Wed/Fri review: which slated specs are
NOT READY and why, which verdicts are pending and for how long, which DL-NN decisions are overdue.
It never approves anything itself, never assigns a tier, never answers a decision, and never edits
check_spec.py. Works inside an SDLC project or standalone against any repo with a specs/ directory.
Refinement runs in any phase where specs exist — Foundation onward, and mid-Build for the next
sprint. A gap that lives in a Phase 1 or 2 artifact is fixed through --upstream without regressing the
phase: the artifact is edited in place, the change is recorded, and that phase's layer is refreshed.
The lifecycle and the ready rule are in references/sprint-model.md.
Instructions
-
Resolve mode and repo root:
- Workflow mode (default): look for
.sdlc/state.yaml; pass--state .sdlc/state.yamlto every script. The repo root is the directory containing.sdlc/; the Phase 0–2 artifacts under.sdlc/artifacts/are the context the specs are checked against. - Standalone mode (
--repo <path>, or no.sdlc/state.yamlfound): pass--repo <path>. There is no engagement context to check against — skip the upstream checks in step 5, say so in the agenda header, and run the DoR, vague-line, and verdict steps as usual. A bare.sdlc/directory withoutstate.yamlis still standalone. - Examples show
--state .sdlc/state.yaml; substitute--repo <path>in standalone mode.
- Workflow mode (default): look for
-
Determine the verb from the arguments: (none) → agenda (step 3);
--spec <id|path>→ one spec (step 4);--sprint SNN→ batch over the slate (step 5);validate→ record a verdict (step 6);--upstream --spec <id>→ the no-regression path (step 7).
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 · 293 lines · 0 tokens per session scan A 68b73a38e782
sdlc-refine 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 5,250 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.