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/researchgit 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 | $0.00011 | $0.00255 |
| Opus 5 | $0.00005 | $0.00128 |
| Sonnet 5 | $0.00002 | $0.00051 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
research 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.
What it actually says
Research Playbook
This is a research task. Do NOT write code unless explicitly asked.
1. Understand the Question
- What specifically needs to be answered?
- What decision does this research inform?
2. Search
- Check existing project docs first (docs/, README, CLAUDE.md)
- Search the codebase for prior art
- Search the web for current information
- Use context7 MCP for library/framework docs
- Always verify versions are current — training data may be stale
3. Synthesize
- Distinguish facts from opinions
- Note when sources conflict
- Include URLs for all external claims
- Flag anything that might be outdated
4. Output
Write findings as a concise summary:
- Answer: the direct answer in 1-3 sentences
- Options: if comparing alternatives, a short pros/cons table
- Recommendation: what you'd pick and why
- Sources: links
If findings are substantial, write them to a file (e.g. research-{topic}.md)
so they persist for future sessions.
$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.
- yesterday First seen · 38 lines · 11 tokens per session scan A d51d42ccc8f3
research is a command published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 255 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.