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/featuregit 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 | $0.00016 | $0.00569 |
| Opus 5 | $0.00008 | $0.00284 |
| Sonnet 5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
feature 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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Feature Playbook
This playbook runs under CLAUDE.md §4 Execution Loop: one phase at a time, parallel review agents at each checkpoint, per-checkpoint report format.
1. Understand
- Read
primer.mdfor current state (if not already in context). - Clarify requirements: what does "done" look like? Inputs, outputs, edge cases, failure modes.
- If vague, outline what you'd build and where. Get approval before coding.
2. Plan
- List the files you'll create or modify, grouped by phase.
- Max 5 files per phase. Each phase is independently shippable.
- For non-trivial features (3+ steps or architectural decisions): enter plan mode, write a spec, get approval before writing code.
- Capture the intended behavior in one paragraph — this is what review agents will check against.
3. Build + test one phase at a time
Per CLAUDE.md §4:
- Implement the phase. Keep scope to the named files.
- Write tests in the same turn — not as a follow-up.
- Follow existing project patterns; read similar code first.
- For non-trivial code exploration, prefer SocratiCode MCP tools over raw grep.
- No speculative abstractions. Build what was asked.
4. Checkpoint review (mandatory, in parallel)
After each phase, spawn review agents in a single message:
code-reviewer— spec compliance + qualitysecurity-reviewer— if the phase touches auth, inputs, DB queries, or APIstest-runner— run the suite, report resultsaccessibility-reviewer— if the phase touches UI
Every reviewer must receive: the task description, the intended behavior paragraph from step 2, and the list of files in this phase. A reviewer without intent cannot judge correctness.
Fix all valid findings before starting the next phase. For any finding you dispute, state why in one sentence.
5. Report (per phase — use the §4 format)
Task: <phase name>
Implementation: <files touched, approach>
Tests: <what was tested, pass/fail counts>
Review findings: <bullets from each reviewer, or "clean">
Fixes: <what changed, or "none">
Status: <complete | blocked: reason>
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.
- yesterday First seen · 63 lines · 16 tokens per session scan A 09d344fc0d25
feature is a command published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 569 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.