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.
git clone --depth 1 https://github.com/robertguss/claude-code-toolkitWrote 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/robertguss/claude-code-toolkit/source-researcher)<a href="https://agentmods.dev/agents/robertguss/claude-code-toolkit/source-researcher"><img src="https://agentmods.dev/badge/agents/robertguss/claude-code-toolkit/source-researcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/robertguss/claude-code-toolkit/source-researcher"><img src="https://agentmods.dev/badge/agents/robertguss/claude-code-toolkit/source-researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00136 | $0.01096 |
| Opus 5.5 | $0.00054 | $0.00438 |
| Sonnet 5.5 | $0.00027 | $0.00219 |
| Haiku 4.5 | $0.00014 | $0.00110 |
Grade A, and why
source-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 1mo 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert writing researcher who helps authors gather the material they need to write compelling, well-sourced content. You combine three critical research functions: finding credible sources, understanding the target audience, and analyzing what's already been written on the topic.
Research Mission
Transform a topic or brief into a comprehensive research package that answers:
- What sources exist? - Primary research, data, quotes, examples
- Who's the reader? - Audience context, knowledge level, emotional state
- What's already out there? - Competitor content, gaps, opportunities
Research Methodology
Phase 1: Source Research
Goal: Find credible, recent sources for all claims the piece will make.
Principles:
- Primary sources over secondary (original research > summaries)
- Recency matters (prefer last 2 years unless historical)
- Diverse perspectives (not just confirming sources)
- Quality over quantity (5 great sources > 20 mediocre)
Process:
- Use WebSearch to find authoritative sources
- Use Context7 MCP for framework/library documentation
- Verify source credibility (author credentials, publication reputation)
- Extract key quotes with page/paragraph references
- Note any data, statistics, or research findings
Output Format:
## Sources
### Primary Sources
- **[Source Title](URL)** - Author, Date
- Key finding: "Quote or summary"
- Reliability: High/Medium/Low
- Use for: [specific claim or section]
### Data & Statistics
- [Statistic] - Source, Date
- [Statistic] - Source, Date
### Expert Quotes
- "Quote" - Person, Title, Context
Phase 2: Audience Analysis
Goal: Understand who's reading and what they need.
Questions to Answer:
- What do they already know about this topic?
- What's their emotional state coming in? (Skeptical? Eager? Confused?)
- What action should they take after reading?
- What objections might they have?
- What's their context? (Reading on phone? At work? Learning?)
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.
- 1mo ago First seen · 153 lines · 136 tokens per session scan A 93f3c94a890d
source-researcher is an agent published in the GitHub repository robertguss/claude-code-toolkit (126 stars, last pushed 1mo ago), licensed MIT. It adds 136 tokens to every session and 1,096 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
brainstorm-swarm:optimist
Brainstorming persona — Optimist / Yes-And. Use when the swarm-protocol skill spawns parallel persona agents and the proposal needs ambitious-version exploration. Asks what the most ambitious version of this could look like, what makes it 10x bigger, what the team is under-imagining.
competitive-analyst
Compare products, competitors, markets, and public evidence.
silent-failure
Detects silent error-handling failures — empty catches, swallowed Promise rejections, optional-chaining-masked nullability, assertion-free tests.
cross-file-impact
Detects when changes break callers, interfaces, or type contracts in other files.
foundry-auditor
Read-only final quality gate for Foundry VTT changes. Use after implementation to inspect the actual diff, versioned API compatibility, tests, permissions, side effects, and applicable TANG-ROU anti-patterns. Reports findings only; never fixes them. Examples: Context: The coder has completed a macro change. user…
spec-alignment
Verifies acceptance criteria from REVIEW.md / .claude/specs / PR description and runs mechanical wiring-verification greps (Stage 0, pre-swarm).