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-channelgit 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-channel)<a href="https://agentmods.dev/commands/mckruz/claude-code-sdlc/sdlc-channel"><img src="https://agentmods.dev/badge/commands/mckruz/claude-code-sdlc/sdlc-channel.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 | $0.01562 |
| Opus 5 | $0.00000 | $0.00781 |
| Sonnet 5 | $0.00000 | $0.00312 |
| Haiku 4.5 | $0.00000 | $0.00156 |
Grade A, and why
sdlc-channel 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc-channel — Bind a Spec to Its Channel and Inject the Acceptance Dimensions
Bind one spec to its delivery channel and overlay that channel's acceptance dimensions onto the
spec's existing ## Acceptance Checks. This is the bind beat after /sdlc-feature (decompose) and
/sdlc-experience (author): decompose → author → bind. It reads the channel descriptor and the
Phase-2 interaction spec, injects concrete checks, seeds harness_context, sets the channel: field,
then runs the advisory check_channel.py beside the byte-for-byte-unchanged check_spec.py.
Interview-driven like /sdlc-coach at the confirmation step: the command proposes the overlay; a named
human decides.
Command-only — it orchestrates the descriptors and the experience artifacts; it spawns no discipline
agent of its own (though it may compose the visual-designer/conversation-designer if the interaction
spec is missing). Works inside an SDLC project or standalone.
Instructions
-
Resolve context:
- Workflow mode (default):
.sdlc/state.yamlexists. The repo root is the directory containing.sdlc/; the interaction spec is.sdlc/artifacts/02-design/experience/channel-interaction-spec.md; metrics log to.sdlc/metrics/channel-log.jsonl. - Standalone mode (
--repo <path>, or no.sdlc/found): operate on the given repo with provisional context; take the interaction spec from--interaction-specif given.
- Workflow mode (default):
-
Resolve the target spec and its channel: Take the spec from
--spec(required if ambiguous) and the channel from--channel, the spec'schannel:field, or the feature-brief row (ask if none). If the spec already sets a differentchannel:, stop and confirm with the human — a spec is one channel. -
Load the descriptor and the interaction spec: Read
channels/<channel>.yamlfor the channel's Acceptance Dimensions (id/intent/example_check),harness_context_seed, andrisk_floor. Read the Phase-2channel-interaction-spec.mdif present — its dimension → contract → acceptance-check rows are the concrete, feature-specific checks to inject. If neither the descriptor nor the interaction spec exists, tell the human to add the descriptor (channels/_template.yaml→validate_channel.py) or run/sdlc-experiencefirst.
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 · 98 lines · 0 tokens per session scan A bb3207f1a051
sdlc-channel is a command published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,562 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
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.