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-specgit 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-spec)<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-spec"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-spec.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 | $0.01343 |
| Opus 5 | $0.00000 | $0.00672 |
| Sonnet 5 | $0.00000 | $0.00269 |
| Haiku 4.5 | $0.00000 | $0.00134 |
Grade A, and why
sdlc-spec 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc-spec — Author a Ready Spec for the Build Loop
Turn a story into a ready spec (specs/NNNN-name.md) that clears the Definition of Ready
before anyone builds it. This is the Intent beat of the Build loop wrapped as one command: scaffold
→ author → enforce the DoR → confirm the risk tier with a human. No spec, no build.
The spec is the durable per-change record — one spec = one branch = one PR. It lives in the repo's
specs/ directory (in version control, not only under .sdlc/), because the agent re-reads it every
session and the grader grades against it.
Instructions
-
Resolve mode and repo root:
- Workflow mode (default): look for
.sdlc/state.yaml. The repo root is the directory containing.sdlc/. Read the spec backlog andrisk-tier-map.mdfrom Foundation for context. - Standalone mode (
--repo <path>, or no.sdlc/found): operate on the given repo with provisional context. Note the missing engagement context in the spec'ssourcefield.
- Workflow mode (default): look for
-
Gather Intent. From the story or the user's request, draft the spec content. Drive the Definition of Ready — do not let any of these stay implicit:
- Goal — one sentence: what capability exists when this is done.
- Why — the outcome that makes this worth building.
- Scope in / Scope out — both stated. What the change must not touch is load-bearing.
- Acceptance checks — each one testable. Apply the vague-line test to every line: "Could two people build different things from this?" If yes, rewrite it with a concrete value (a status code, a JSON body, a count, a path) until they couldn't.
- Silent decisions — surface every unwritten product choice (fail open or closed? what does a blocked user see?) onto the spec's Decision List with a named human owner and an answer clock. The agent must not guess these.
- Harness context — name the ONE existing pattern this change reuses, so the agent extends the codebase instead of inventing a second way to do something.
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 · 87 lines · 0 tokens per session scan A d9229dbe1429
sdlc-spec is a command published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,343 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.