Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/mckruz/claude-code-sdlc/sdlc-featuregit clone --depth 1 https://github.com/MCKRUZ/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-feature)<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-feature"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-feature.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 | $0.00000 | $0.01466 |
| Opus 5 | $0.00000 | $0.00733 |
| Sonnet 5 | $0.00000 | $0.00293 |
| Haiku 4.5 | $0.00000 | $0.00147 |
Grade A, and why
sdlc-feature 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 3d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc-feature — Decompose an Epic into Channel-Aware Features and Specs
Drive the epic → feature → spec decomposition that the plugin lacks today — the "featuring" hop
where you decide how a feature is delivered (which customer channels, which personas) and carve it
into buildable specs. Output is feature-brief.md, authored on every channel-bound feature. This is
interview-driven like /sdlc-coach: the feature-architect agent assesses what's there, asks focused
questions, and drafts the brief as answers arrive — it proposes, a named human decides (the One
Rule). Works inside an SDLC project or standalone against any repo.
Instructions
-
Resolve context:
- Workflow mode (default):
.sdlc/state.yamlexists. Read the epic from.sdlc/artifacts/01-requirements/epics.md, the requirements fromrequirements.md, and anyuser-stories.md; the brief lands in.sdlc/artifacts/01-requirements/feature-brief.md. - Standalone mode (
--repo <path>, or no.sdlc/found): operate on the given repo with provisional context. Note the missing engagement context in the brief's header and write it to the given--output(default alongside the repo).
- Workflow mode (default):
-
Assess what exists: Read the epic and any prior requirements/persona/channel-sensing work. The feature-brief sits below the epic — it decomposes one epic into features + specs; it does not replace
epics.mdor the stories. If no epic is available, ask the human to name the epic and its outcome before decomposing. -
Run the interview: Spawn the
feature-architectagent (Product discipline). It runs the coach-style dialogue — which epic; the single coherent slice of value (the feature); who the customer is and how they reach it (the channel is sensed here); whether there is shared "brains" logic multiple surfaces reuse (a channel-agnostic spec); and any product choice not yet decided that the agent must not guess. It draftsfeature-brief.mdfromtemplates/phases/01-requirements/feature-brief.md— each##section names its owning discipline, with a Channels × personas narrative and a decomposition table whose rows carry channel + persona columns. Channel-agnostic rows (channel: —) are first-class — the shared brains the surfaces build on. One channel per spec.
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.
- 3d ago First seen · 92 lines · 0 tokens per session scan A c07e37ec5fc3
sdlc-feature is a command published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,466 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.