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/codeverbojan/claude-code-kickstart/onboardgit clone --depth 1 https://github.com/codeverbojan/claude-code-kickstartWhat 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 | $0.00018 | $0.00402 |
| Opus 5 | $0.00009 | $0.00201 |
| Sonnet 5 | $0.00004 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
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.
What it actually says
Session Onboard
primer.md is auto-loaded by the SessionStart hook, so skip anything that
just re-reads it. Mode is determined by $ARGUMENTS.
DEEP MODE — if $ARGUMENTS contains "deep"
Full context load for major work. Read in this order, skipping any file that
contains a placeholder stub (No gotchas yet, No patterns extracted yet,
No decisions logged yet) — those have no signal:
gotchas.md,patterns.md,decisions.md(non-stub only)- Project structure: key directories, entry points, top-level config
- Architecture docs if present (
docs/,ARCHITECTURE.md,README.md) git statusfor uncommitted state- Typecheck/lint if configured — otherwise skip silently
Report in under 15 lines:
- Current state (from primer.md)
- Project structure (one line)
- Uncommitted changes
- Test/lint health or "not configured"
- Next steps from primer.md
- Blockers or clarifications needed
If a task was given alongside "deep", also name the 1–3 files you'll need and how the task fits the current state.
LIGHT MODE — if a task is given (no "deep")
Fast onboard for focused work.
- Identify the 1–3 files most relevant to
$ARGUMENTS - Report in 3–5 lines: current state, what you'll work on, files you'll touch, any blocker
- Start working immediately.
STATUS MODE — no arguments
Just report git status + next steps from primer.md in 3 lines. Don't
re-read primer.md — it's already in context. Wait for instructions.
$ARGUMENTS
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 · 49 lines · 18 tokens per session scan A 98154110d762
onboard is a command published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 402 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 2026-08-31.
Other commands, from other repositories
stats
Show token-saver compression statistics and savings.
implement
Execute implementation by processing atomic task files one at a time with Context Pinning (Atomic Traceability Model).
cleanup
Detect and remove orphaned code, unused components, dead routes, and stale database artifacts.
specify
Create or update the feature specification from a natural language feature description.
_registry-protocol
This protocol is MANDATORY for ALL commands, agents, and phases.
amby.converge
Check the codebase against spec, plan, and tasks after implementing; append gap tasks, never edit code.