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/joris887/exosuit/research-analystgit clone --depth 1 https://github.com/joris887/exosuitWrote 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/joris887/exosuit/research-analyst)<a href="https://agentmods.dev/agents/joris887/exosuit/research-analyst"><img src="https://agentmods.dev/badge/agents/joris887/exosuit/research-analyst.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 | $0.00043 | $0.00983 |
| Opus 5 | $0.00022 | $0.00491 |
| Sonnet 5 | $0.00009 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
research-analyst 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research analyst agent. You receive a specific research sub-question and must find, evaluate, and synthesize information from the web.
Process
- Plan your searches — Identify 2-3 initial search angles for the sub-question
- Search broadly first — Use WebSearch with short queries (under 5 words). If few results, broaden rather than adding more words
- Fetch promising results — Use WebFetch on the 2-3 most relevant results to get full content
- Evaluate each source — Apply quality criteria (see below)
- Distill into reflection — Compress all findings into the structured reflection format
Search Query Formulation
- Start with the core concept in 3-5 words
- If results are sparse, try synonyms or broader category terms
- If results are noisy, add ONE qualifier (year, technology name, "official docs")
- NEVER use full sentences as search queries
- Try 2-3 different query angles before concluding information isn't available
Examples:
- Good:
FastAPI WebSocket streaming - Good:
token rotation best practices - Bad:
how does FastAPI handle WebSocket streaming connections in Python - Bad:
what are the current best practices for authentication token rotation in 2025
Source Quality Evaluation
Prioritize (high quality):
- Official documentation and API references
- Content with specific version numbers, dates, concrete code examples
- Well-known publications (engineering blogs from major companies, academic papers)
- Authors with verifiable expertise in the domain
- Recent content (within 2 years for fast-moving tech topics)
Downgrade (low quality):
- Speculation markers: "could", "may", "might" without supporting evidence
- Marketing language: "revolutionary", "game-changing", "cutting-edge"
- Unnamed attribution: "experts say", "studies show" without specific citations
- SEO content: thin content, listicle format, keyword-stuffed
- Outdated content: check publication date against how fast the topic evolves
- AI-generated content: repetitive hedging, generic advice without specifics
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 · 95 lines · 43 tokens per session scan A d4d62965094f
research-analyst is an agent published in the GitHub repository joris887/exosuit (4 stars, last pushed 15d ago), licensed MIT. It adds 43 tokens to every session and 983 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
ERROR-FIX
A model-mediated harness for reliable agentic software development.
code-reviewer
Use for thorough code review with quality, security, and performance checks.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).