Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lantisprime/claude-sdlcnpx agentmods add skills/lantisprime/claude-sdlc/analyzeWrote 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/analyze)<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/analyze"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/analyze/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/analyze"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/analyze.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00111 | $0.00999 |
| Opus 5.5 | $0.00044 | $0.00400 |
| Sonnet 5.5 | $0.00022 | $0.00200 |
| Haiku 4.5 | $0.00011 | $0.00100 |
Grade A, and why
analyze 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze (Phase 2)
Turn a task into structured, testable requirements.
Prerequisite
The plan gate must exist: .claude/sdlc/gates/plan-<task-slug>.md. If it does not, tell the human to run /plan first.
Step 1 — Detect frontend involvement
Before writing requirements, determine whether the task touches a user interface. Check:
- The plan's in-scope files for UI frameworks (React, Vue, Angular, HTML templates, mobile views)
- Keywords in the plan: "screen", "page", "form", "button", "UI", "UX", "design"
If yes, and no UX artifact exists under .claude/sdlc/architecture/ux/:
- Halt. Ask the human for UX designs (Figma link, wireframes, mockups) and brand guidelines (colors, typography, spacing tokens, component library).
- Do not proceed to write requirements until a UX artifact is linked or written at
.claude/sdlc/architecture/ux/<task-slug>.md.
This is a hard rule. Frontend without UX specs produces UI debt.
Step 2 — Write requirements
Write to .claude/sdlc/requirements/<task-slug>.md using templates/requirements.md. Each requirement has:
- Stable ID:
REQ-<n>— never renumbered once published - Title: short imperative
- Description: what the system must do
- Acceptance criteria: testable, unambiguous (Given/When/Then works)
- Priority: must / should / could
- Source: ticket, CR, stakeholder, or project scope section
- Dependencies: other REQ IDs or external systems
Stable IDs matter: Design references them, Build validates against them, Test maps cases to them, Deploy records them, Docs traces them.
Step 3 — Contract / scope coverage check
For each requirement, confirm it maps to a section of .claude/sdlc/scope.md (or the relevant contract/SOW artifact). Any unmapped requirement is a scope question — surface it, don't hide it. The human decides whether to expand scope or drop the requirement.
Produce a coverage table in the requirements file:
| REQ ID | Scope section | Status |
|---|---|---|
| REQ-001 | 2.1 Checkout | ✓ mapped |
| REQ-002 | — | ? unmapped |
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.
- 1mo ago First seen · 86 lines · 111 tokens per session scan A 2eb48cfbee63
analyze is a skill published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 5mo ago), licensed MIT. It adds 111 tokens to every session and 999 once invoked, about $0.0004 per session on Opus 5.5. 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
handoff
Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why. Saves it to project memory so the next chat sees it at the start, and prints it so it can be pasted into a message or a pull request. Use when the user ends a piece of work…
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…
done-blocked
Reusable reporting contract for any agent that hands work back to the pipeline. Forces ONE of two terminal statuses (DONE or BLOCKED) with a specific evidence shape. Stops vague "probably finished" and "kind of stuck" verdicts.
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.
goga-task-by-specifying
Interactive task formulation from a raw request.