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/analyzenpx skills add lantisprime/claude-sdlc --skill analyzegit 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/analyze)<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/analyze"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/analyze.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 | $0.00111 | $0.00999 |
| Opus 5 | $0.00056 | $0.00500 |
| Sonnet 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 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 — 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.
- 4d 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 4mo ago), licensed MIT. It adds 111 tokens to every session and 999 once invoked, about $0.0006 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
harvest
Sprint analytics — type distributions, stale claims, velocity, prediction scoring.
feedback
Record stakeholder input — new constraints, corrections, or direction changes.
status
Show a snapshot of the current sprint -- claims, conflicts, coverage, and next actions.
pull
Pull a sprint from Confluence and import it as local claims.
wf-pm
Sole team lead of the waterfall workflow — creates the team, dispatches OR's spawnrequest, relays HO decisions via AskUserQuestion, and runs the final git commit at CLOSURE.
wf-pm-light
PM solo pour le mode subagent-light — élicitation, specs.md, checkpoint specs, spawn TL passe 1+2, checkpoint tasks, validation finale, git commit.