Borrowing it
Nothing to install: this file belongs to cas-team-analyst/team-analyst. 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/cas-team-analyst/team-analyst/main/CLAUDE.mdgit clone --depth 1 https://github.com/cas-team-analyst/team-analystWrote 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/instructions/cas-team-analyst/team-analyst/claude-md)<a href="https://agentmods.dev/instructions/cas-team-analyst/team-analyst/claude-md"><img src="https://agentmods.dev/badge/instructions/cas-team-analyst/team-analyst/claude-md/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/instructions/cas-team-analyst/team-analyst/claude-md"><img src="https://agentmods.dev/badge/instructions/cas-team-analyst/team-analyst/claude-md.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 | $0.02319 | $0.02319 |
| Opus 5.5 | $0.00928 | $0.00928 |
| Sonnet 5.5 | $0.00464 | $0.00464 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade B, and why
team-analyst CLAUDE.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `import/teamanalyst-plugin-other.zip` | Built by `create_import_zips.py`. Root `plugin.json` plus `skills/`, for unzipping into `~/.cursor/plugins/local/`, `~/.gemini/config/plugins/` or `.agents/plugins/`. | How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — TeamAnalyst
README is a product artifact
The README is the install surface for this repo. Treat it like product copy, not internal notes.
Rules for README changes:
- Keep install commands accurate for every tool in the "Installation for Other Agentic Tools" section. Tools are grouped by provider (Anthropic, OpenAI, Google, Microsoft, GitHub, Other tools).
- Each tool section starts with the install command. Tools with no terminal command start with the italic line "There is no terminal command to install the skill into this tool." and then give the UI steps.
- Only list a tool once its install path is verified against the vendor's docs, and link those docs.
- Keep the bundle story clear: TeamAnalyst installs all skills and all selector/reference agents together.
- Prefer language that a non-specialist can follow without knowing how agent plugins work internally.
- If packaging behavior changes, update the install section and the "Helpful Commands" zip-build instructions in the same change.
- If you change the skills, run
python create_import_zips.py.
Project overview
TeamAnalyst is a skill-and-script bundle for actuarial reserve analysis workflows. It packages multiple skills, selector prompts, and Python helper scripts so AI coding agents can guide or execute a repeatable reserving workflow.
The core user-facing workflow is reserving-analysis, supported by:
peer-reviewfor reviewing a completed analysis
skills/ ships exactly these two skills. Contributor-only helper skills (python, excel-formulas, improve-agent, and the caveman skills) live in .claude/skills/ and .agents/skills/, are not part of the shipped bundle, and must not be referenced from shipped files.
The selector files in skills/reserving-analysis/agents/ are custom subagents consumed by the workflow (six selector-*.agent.md files covering chain ladder LDFs, tail curves, and ultimates, each in a framework and an open-ended variant). They must stay aligned with the workflow instructions in skills/. There is no separate skill for viewing or explaining selection logic; agents and users refer directly to the selector agent files in skills/reserving-analysis/agents/.
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 Changed · +22 lines · +888 tokens per session scan A → B 692ae81ae8b4
- 2mo ago Changed · +2 tokens per session ea34382f4aeb
- 2mo ago First seen · 132 lines · 1,429 tokens per session scan A cc14ffae9a29
team-analyst CLAUDE.md is an instructions file published in the GitHub repository cas-team-analyst/team-analyst (12 stars, last pushed 1mo ago), licensed MIT. It adds 2,319 tokens to every session, about $0.0093 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
team-analyst CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| team-analyst CLAUDE.mdcas-team-analyst/team-analyst | Instructions file | 12 | 1mo ago | MIT | B | 2,319 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |