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/loiane/specs-driven-development-spring-angular/onboardgit clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angularWhat 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 | $0.00019 | $0.00727 |
| Opus 5 | $0.00010 | $0.00364 |
| Sonnet 5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
onboard 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 2d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/onboard
Phase: 0 — bootstrap
Owning agent: .claude/agents/spring-onboarding.md
Skills used: brownfield-onboarding, maven-harness-pom, flyway-or-liquibase-detection, harness-report-parsing, archunit-rules
Purpose
Inspect the repository, classify it as greenfield or brownfield, capture a baseline harness run, and produce .specs/_onboarding.md so future commands know the stack.
Inputs
None required. Optional argument: a path to constrain the scan.
- For a single-project repo: omit the argument; the script reads
./pom.xml. - For a multi-module Maven build: pass the submodule directory.
- For a polyglot monorepo (e.g. Spring Boot backend + Angular/React frontend in sibling top-level dirs): pass the Maven module directory (e.g.
shoply-api). Sibling non-JVM apps are auto-detected and recorded undersiblingsin_stack.jsonand as context-only notes in_onboarding.md. The harness only validates the Maven module; frontend tooling is owned by its own pipeline.
Reads
pom.xml(root and any submodules)src/main/**,src/test/**(counts only)db/migration/**,db/changelog/**- Existing
.specs/if any
Writes
.specs/_onboarding.md.specs/_stack.json(output of.github/scripts/detect-stack.sh).specs/_baseline.json(only if any test exists; output of.github/scripts/harness.sh --baseline)
Process
- Resolve the Maven module path (
MODULE= optional arg, else.). Run.github/scripts/detect-stack.sh "$MODULE/pom.xml" > .specs/_stack.json. Refuse to proceed ifmigration == "both". - Count source/test files under
$MODULE/src/; classify:- Greenfield if no
src/main/java/**or only the Spring BootApplication.java(auto-generated*ApplicationTests.javaandTestcontainers*.javascaffolding do not change the classification). - Brownfield otherwise.
- Greenfield if no
- If brownfield, run
.github/scripts/harness.sh --module "$MODULE" --baselineand capture results. Do NOT attempt to fix failures. - Diff
$MODULE/pom.xmlagainst.claude/maven/parent-pom-fragment.xml; list missing harness layers as Findings. - Write
.specs/_onboarding.mdcovering: classification, module path, sibling apps (if any), stack JSON, baseline gate results (or “N/A — greenfield”), missing layers, recommended/specstarting point.
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.
- 2d ago First seen · 48 lines · 19 tokens per session scan A e423be4e3cec
onboard is a command published in the GitHub repository loiane/specs-driven-development-spring-angular (58 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 727 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
devkit.refactor
Provides guided code refactoring capability with deep codebase understanding, compatibility options, and comprehensive verification. Use when restructuring or improving existing code.
spec-kitty.analyze
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
devkit.verify-skill
Validates a skill against DevKit standards (requirements, template, dependencies). Use when you need to verify a skill before publishing or after modifications.
devkit.prompt-optimize
Provides expert prompt optimization using advanced techniques (CoT, few-shot, constitutional AI) for LLM performance enhancement. Use when you need to improve prompt quality or optimize LLM interactions.
sdd-plan
Turn a spec into a persisted baby-step plan file — research, resume, impact analysis.
sdd-architecture-update
Detect architecture drift and sync the snapshot + Memory Bank (with confirmation).