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 skills/lantisprime/claude-sdlc/designnpx skills add lantisprime/claude-sdlc --skill designgit clone --depth 1 https://github.com/lantisprime/claude-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/skills/lantisprime/claude-sdlc/design)<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/design"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/design.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 | $0.00109 | $0.00998 |
| Opus 5 | $0.00055 | $0.00499 |
| Sonnet 5 | $0.00022 | $0.00200 |
| Haiku 4.5 | $0.00011 | $0.00100 |
Grade A, and why
design 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design (Phase 3)
Produce the artifacts Build will reference and Test will execute against.
Prerequisite
.claude/sdlc/gates/analyze-<task-slug>.md must exist and be signed.
Artifacts produced (or updated)
All live under .claude/sdlc/architecture/ with a manifest.json index:
- Application architecture — components, integrations, data flow, NFRs (performance, availability, scalability)
- Data architecture — entities, schema changes, flows, retention, classification
- Platform architecture — runtimes, orchestration, environments
- Infrastructure architecture — compute, network, storage, identity
- Security architecture — threat model, controls, secrets handling, authn/authz
- Test architecture — pyramid shape, test types, tooling, environments, test-data strategy
- Technical specifications — API contracts, data contracts, module responsibilities (under
.claude/sdlc/tech-specs/) - Test cases — one or more per requirement, each tied to REQ IDs (under
.claude/sdlc/test-cases/) - DevOps pipeline design — stages, gates, environments, promotion rules
Rule: validate before rewriting
If architecture artifacts already exist:
- Read them.
- Produce a validation report comparing existing architecture against the current requirements set.
- Surface deltas (new NFRs, new entities, new integrations, new controls) for human decision.
- Only after the human agrees, update the affected files. Never wholesale-regenerate a working architecture.
Test-case rule
Each requirement gets at least one test case. Each test case references:
- The REQ IDs it covers
- The test type (unit / integration / e2e / NFR)
- Preconditions, steps, expected outcome
- Data needs
Use templates/test-case.md.
Tech spec rule
For each in-scope module or service, produce or update a spec under .claude/sdlc/tech-specs/. Specs are the contract Build validates its code against — API shape, inputs/outputs, error modes, side effects, NFR commitments.
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 · 96 lines · 109 tokens per session scan A 59a346b8b065
design is a skill published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 109 tokens to every session and 998 once invoked, about $0.0005 per session on Opus 5. 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 skills, from other repositories
setup
Guide the user through verifying Grainulator's MCP servers are running, explain what each server does, handle optional dependencies, and initialize a first sprint if none exists. Use when the plugin is first installed, when MCP servers fail to connect, or when the user asks for help setting up Grainulator.
challenge
Adversarial testing of a specific claim. Try to disprove it.
healthcheck
Fast pre-flight health check for all Grainulator MCP servers. Pings each server once, reports status in a table, and provides exact fix commands for any that are down. Use before starting any Grainulator session to avoid wasting time on MCP disconnections.
fetch
Size-efficient URL fetch with semantic extraction. Use for ad-hoc web research when you want content without the raw HTML overhead.
harvest
Sprint analytics — type distributions, stale claims, velocity, prediction scoring.
orchard
Multi-sprint orchestration — view dependency graph, dispatch next ready sprint.