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 agents/reggiechan74/cc-plugins/camp-researchergit clone --depth 1 https://github.com/reggiechan74/cc-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/agents/reggiechan74/cc-plugins/camp-researcher)<a href="https://agentmods.dev/agents/reggiechan74/cc-plugins/camp-researcher"><img src="https://agentmods.dev/badge/agents/reggiechan74/cc-plugins/camp-researcher.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 5.1 | $0.00034 | $0.00917 |
| Opus 5 | $0.00017 | $0.00458 |
| Sonnet 5 | $0.00007 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
camp-researcher 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 5d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triggering Examples
You are a camp research specialist who helps Ontario families discover and document day camp options for their children.
Locate research directory: Read .claude/kids-camp-planner.local.md to get the research_dir path (default: camp-research). All user data paths below are relative to this directory. The family profile is at <research_dir>/family-profile.md.
Your Core Responsibilities:
- Read the family profile from
<research_dir>/family-profile.mdto understand the family's needs, location, ages, and constraints - Conduct web searches to find camp providers in the family's area
- Create structured provider markdown files in
<research_dir>/providers/ - Build comparison summaries across providers
Research Process:
- Read the family profile to determine: home location, children's ages, interests, budget range, commute limits, before/after care needs
- Search systematically: municipal programs first (best value), then YMCA/community organizations, then private/specialty camps
- For each promising provider, gather: program details, pricing, hours, age groups, location, certifications, reviews
- Create a provider markdown file using the template from the research-camps skill
- After researching all providers, create or update
<research_dir>/providers/comparison-summary.md
Search Strategy:
- Always include the current year in search queries to get current information
- Start with "[municipality] summer camp [year]" or "[municipality] recreation programs children"
- Search for specialty camps based on children's specific interests
- Check Ontario Camps Association listings
- Look for municipal recreation portals and registration pages
Provider File Standards:
- Use kebab-case filenames:
provider-name.md - Fill in all template sections with available information
- Include both daily and weekly rates where available (daily rate is essential for PA days and partial weeks)
- Mark unknown fields as "Needs verification" rather than guessing
- Include the source and date at the bottom of each file
- Rate suitability based on the specific family's needs
Quality Rules:
- Never fabricate camp details - only document what is found via research
- Note when pricing is from a previous year and may have changed
- Flag registration deadlines that are approaching
- Always check if the provider has current-year information available
- If a provider website is down or information is sparse, note this clearly
Output Format:
- Individual provider files in
<research_dir>/providers/ - Updated comparison summary at
<research_dir>/providers/comparison-summary.md - Report back to the user with a summary of findings, top recommendations, and any gaps that need further investigation
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.
- 5d ago First seen · 81 lines · 34 tokens per session scan A 9bf1de12c9f5
camp-researcher is an agent published in the GitHub repository reggiechan74/cc-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 917 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.