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-spikegit 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-spike)<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-spike"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-spike.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 | $0.01213 |
| Opus 5 | $0.00000 | $0.00607 |
| Sonnet 5 | $0.00000 | $0.00243 |
| Haiku 4.5 | $0.00000 | $0.00121 |
Grade A, and why
sdlc-spike 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 4d 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-spike — Run a Bounded Spike When the Answer Isn't Known Yet
Open a spike (spikes/NNNN-name.md) for a question the pod cannot yet answer. This is the
escape hatch for the one situation /sdlc-spec cannot serve: a story that fails the Definition of
Ready not because it is badly written, but because nobody knows the answer.
Writing a confident spec about an unknown is the expensive mistake. It reads as ready, the grader grades it against fiction, and the pod finds out at merge. A spike finds out first.
The spike's deliverable is a written finding, not code. The code is thrown away; the finding is committed and outlives the branch.
When this command applies
Use it when an acceptance check cannot be written because the behavior is unverified:
- An integration's real response is undocumented ("does the carrier API deduplicate on our idempotency key, or do retries create duplicate claims?").
- A design decision rests on an assumption nobody has tested.
- Two people at triage wrote two different acceptance lines for the same requirement — the vague-line test failing out loud because the ground truth is missing.
Do not use it as a way to start building without a spec. If the answer is known and the work just feels large, that is a spec (possibly several).
Steps
-
Confirm it is genuinely an unknown, not a vague line. Ask which acceptance check cannot be written, and why. If the answer is "we know, it just needs wording," stop and run
/sdlc-specinstead. Say so plainly rather than opening a spike to avoid the harder conversation. -
Get the box and the opener from a human. Both are required, and neither is yours to decide.
"How long should this be boxed — a time box or a token box? And who is opening it: the Pod Lead at triage, or the Architect on a design decision?"
A spike with no box is unsupervised building. Claude never decides to spike instead of build.
-
Name what it unblocks. A decision-list item id, the story that cannot be made ready, or the ADR whose assumption is under test. A spike that unblocks nothing is tinkering.
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.
- 4d ago First seen · 90 lines · 0 tokens per session scan A df42402dde02
sdlc-spike 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 1,213 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.