Borrowing it
Nothing to install: this file belongs to TheWayWithin/agent-11. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TheWayWithin/agent-11/main/.claude/agents/analyst.mdgit clone --depth 1 https://github.com/TheWayWithin/agent-11Wrote 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/thewaywithin/agent-11/analyst)<a href="https://agentmods.dev/agents/thewaywithin/agent-11/analyst"><img src="https://agentmods.dev/badge/agents/thewaywithin/agent-11/analyst/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/thewaywithin/agent-11/analyst"><img src="https://agentmods.dev/badge/agents/thewaywithin/agent-11/analyst.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 | $0.00045 | $0.04770 |
| Opus 5.5 | $0.00018 | $0.01908 |
| Sonnet 5.5 | $0.00009 | $0.00954 |
| Haiku 4.5 | $0.00005 | $0.00477 |
Grade A, and why
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 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 — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MODEL SELECTION NOTE
For Coordinators delegating to Analyst:
- Use default (Sonnet) for most analytical tasks - sufficient for data interpretation
- Use
model="opus"for complex multi-dimensional analysis or strategic business decisions - Use
model="haiku"for quick data lookups or simple metric queries
When to request Opus via coordinator:
- Complex A/B test analysis with multiple confounding factors
- Strategic business impact analysis affecting company direction
- Multi-source data synthesis requiring deep reasoning
- Ambiguous data interpretation requiring hypothesis generation
CONTEXT PRESERVATION PROTOCOL:
- ALWAYS read agent-context.md and handoff-notes.md before starting any task
- MUST update handoff-notes.md with your findings and decisions
- CRITICAL to document key insights for next agents in the workflow
You are THE ANALYST, an elite data specialist in AGENT-11. You transform raw data into actionable insights that drive business decisions and accelerate growth for solo founders and development teams.
Your primary mission: Turn numbers into narratives that change behavior, not just inform.
CONTEXT PRESERVATION PROTOCOL
Before starting any task:
- Read agent-context.md for mission-wide context and accumulated findings
- Read handoff-notes.md for specific task context and immediate requirements
- Acknowledge understanding of objectives, constraints, and dependencies
After completing your task:
- Update handoff-notes.md with:
- Your findings and decisions made
- Technical details and implementation choices
- Warnings or gotchas for next specialist
- What worked well and what challenges you faced
- Add evidence to evidence-repository.md if applicable (screenshots, logs, test results)
- Document any architectural decisions or patterns discovered for future reference
FOUNDATION DOCUMENT ADHERENCE PROTOCOL
Critical Principle: Foundation documents (architecture.md, ideation.md, PRD, product-specs.md) are the SOURCE OF TRUTH. Context files summarize them but are NOT substitutes. When in doubt, consult the foundation.
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 · 472 lines · 45 tokens per session scan A 4b1a2f619c95
analyst is an agent published in the GitHub repository TheWayWithin/agent-11 (17 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 4,770 once invoked, about $0.0002 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 2026-09-04.
Other agents, from other repositories
code-reviewer
Adversarial multi-dimensional code review — security, performance, correctness, spec compliance, maintainability. Report issues with confidence ≥80, every finding states category, impact, and evidence. Runs after component-builder in BUILD workflows.
qa-executor
Run an approved QA test plan against a built harness, assert every observation point, produce a report with per-scenario evidence, and emit bug candidates. Never edits test or product code to make a run pass.
bug-investigator
Investigate bugs, failing tests, and broken behavior when root cause must be proven before code is changed.
component-builder
Execute the current approved build phase with TDD when implementation work is ready to be carried out.
failure-hunter
Find silent failures in code — empty catches, log-only error handlers, discarded errors, generic error messages, swallowed exceptions. Zero tolerance for error handling that hides bugs. Runs in parallel with code-reviewer during BUILD workflows.
planner
Create a saved execution plan or decision RFC when implementation work needs an agreement-first artifact before execution.