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/anilcancakir/claude-code-plugins/my_researchgit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWrote 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/commands/anilcancakir/claude-code-plugins/my_research)<a href="https://agentmods.dev/commands/anilcancakir/claude-code-plugins/my_research"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code-plugins/my_research.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 | $0.00018 | $0.01028 |
| Opus 5 | $0.00009 | $0.00514 |
| Sonnet 5 | $0.00004 | $0.00206 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
my_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 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Command
Execute comprehensive business research workflow.
Arguments
Required:
topic- The research subject (business idea, market, competitor, etc.)
Optional Mode:
--quick- Quick overview (~15-20 min)--standard- Detailed analysis (~30-45 min) [default]--deep- Comprehensive validation (~60+ min)
Usage Examples
/my_research "AI-powered code review tools" --quick
/my_research "competitor analysis for Notion alternatives" --standard
/my_research "validate SaaS idea for developer analytics" --deep
Research Workflow
Step 1: Scope Definition
Confirm research parameters with user:
- Topic/idea to research
- Research mode (quick/standard/deep)
- Specific questions to answer
- Geographic/segment focus if relevant
Step 2: Execute Research by Mode
Quick Mode (--quick):
- Gather high-level market data
- Identify top 3-5 competitors
- Assess timing (good/neutral/poor)
- Generate quick report template
- Save to
.claude/research/[topic]-quick-[date].md
Standard Mode (--standard):
- Calculate TAM/SAM/SOM with multiple sources
- Profile 5-7 Tier 1 competitors in detail
- Apply Porter's Five Forces framework
- Identify 3-5 major trends
- Generate standard report template
- Save to
.claude/research/[topic]-standard-[date].md
Deep Mode (--deep):
- Delegate to
market-researcheragent for market sizing - Delegate to
trend-analyzeragent for timing assessment - Delegate to
idea-validatoragent for validation scoring - Compile comprehensive SWOT analysis
- Generate actionable recommendations
- Generate deep report template
- Save to
.claude/research/[topic]-deep-[date].md
Step 3: Agent Delegation (Deep Mode)
When in deep mode, use specialized agents:
Use the market-researcher agent to analyze market size and industry dynamics for [topic]
Use the trend-analyzer agent to assess timing and emerging patterns for [topic]
Use the idea-validator agent to score and validate [idea] against the 5-dimension framework
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 · 162 lines · 18 tokens per session scan A dc4517f180e3
my_research is a command published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 1,028 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
debug
Systematic debugging with hypotheses and evidence gathering.
health
Run the Self-Star Doctor - a green/yellow/red health board across all 7 junctions of the self- loop.
plan-new
Plan a complex project with discovery, structure, and kill criteria.
create-hook
Create a new custom automation hook.
remember
Explicitly save something to memory as an experience.
context-stats
Show context window usage, active tier, and system stats.