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/plannpx skills add lantisprime/claude-sdlc --skill plangit 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/plan)<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/plan"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/plan.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 | $0.00130 | $0.02847 |
| Opus 5 | $0.00065 | $0.01424 |
| Sonnet 5 | $0.00026 | $0.00569 |
| Haiku 4.5 | $0.00013 | $0.00285 |
Grade A, and why
plan 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan (Phase 1)
Produce a plan artifact before any code is touched. The plan-gate hook blocks Edit/Write until this file exists.
Step 1 — Classify the work item
Ask (or infer from context) which of these the request is:
- New build — a new feature or capability not previously delivered
- Fix — a correction to existing behavior
- Change request (CR) — a modification to previously agreed scope
The classification drives different validation downstream (Phase 4 Build).
Step 2 — Resolve scope
If .claude/sdlc/scope.md exists and is signed: read it and proceed. Run a quick re-validation check — if the plan task looks materially different from what scope.md describes, invoke scope-ingest in re-validate mode and surface the drift report before continuing.
If .claude/sdlc/scope.md does not exist: ask the human to point at source material (file path or paste text). Then invoke the scope-ingest agent, which produces a draft at .claude/sdlc/scope-drafts/<timestamp>.md. Show the draft to the human and wait for review. The human copies/renames it to .claude/sdlc/scope.md and signs it before the plan proceeds.
Fallback — no source material: if the human has no source to point at, ask for a one-paragraph scope statement and write .claude/sdlc/scope.md directly (existing behavior, preserved for minimal-friction cases).
Then validate the resolved scope against the work item:
- New build: confirm the request is within documented scope. If not, surface a scope-delta and ask the human whether to (a) treat as a CR, (b) expand scope, or (c) defer.
- Fix: confirm the fix addresses in-scope behavior. An out-of-scope fix is a CR in disguise.
- CR: require a change-request ID. If missing, create one under
.claude/sdlc/change-requests/CR-<n>.mdusingtemplates/change-request.mdand ask the human for sign-off before continuing.
See agents/scope-ingest.md for accepted source formats and draft output spec.
Step 2.5 — Domain expert check
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 · 193 lines · 130 tokens per session scan A 05e7595e4ac6
plan is a skill published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 130 tokens to every session and 2,847 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
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.
harvest
Sprint analytics — type distributions, stale claims, velocity, prediction scoring.
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.
orchard
Multi-sprint orchestration — view dependency graph, dispatch next ready sprint.
blind-spot
Structural gap analysis -- find what the sprint has not considered.