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 instructions/royashbrook/lifescored/agents-mdgit clone --depth 1 https://github.com/royashbrook/lifescoredWrote 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/royashbrook/lifescored/agents-md)<a href="https://agentmods.dev/instructions/royashbrook/lifescored/agents-md"><img src="https://agentmods.dev/badge/instructions/royashbrook/lifescored/agents-md.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 | $0.00904 | $0.00904 |
| Opus 5 | $0.00452 | $0.00452 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
lifescored AGENTS.md 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 3d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
lifescored.com — a Svelte 5 / SvelteKit transparency app on Cloudflare
Workers that rebuilds the scores real systems already run on people (credit bureaus, actuarial life
tables, lenders, audit studies), in the open: every rule cited or flagged as a guess, every weight
editable. This is the vendor-neutral guide for any agent. (Claude Code reads CLAUDE.md, which points
here.)
Using lifescored AS an agent (to compute a score)
You don't need this repo, and you must never send a person's answers to lifescored.com — it computes on your side:
- Skill:
skills/lifescored/SKILL.md— drop it into your agent's skills directory. - Rulebook + exact math:
https://lifescored.com/rules.json· index…/llms.txt· full prose…/llms-full.txt - MCP server:
com.lifescored/mcp(tools:get_rulebook,get_input_schema,get_methodology,how_to_give_feedback)
Working ON this repo
Setup
npm install # also installs the commit-msg hook (core.hooksPath → .githooks)
The gate — all must pass before a PR merges
npm run check # svelte-check + types
npm test # vitest: rulebook invariants, engine, codec, worker handler
npm run test:e2e # playwright
npm run build
Conventions
- Every commit references a GitHub issue, e.g.
feat: add presets (#2). Acommit-msghook enforces it (merges/reverts exempt). Find or open one:gh issue list/gh issue create. - Branch → PR → merge to
main. CI runs the full gate, then builds and deploys (.github/workflows/deploy.yml). Don't commit straight tomain. - Single source of truth:
rules.json,llms-full.txt, and the MCP server are all generated fromsrc/lib/rulebook/export.ts. Never hand-edit a generated output — change the rulebook or the generator and they all update together.
The rulebook
Rules live in src/lib/rulebook/<domain>.ts, declarative: a pure position(inputs) (the measured
fact, normalized 0–1), bounds (negative only where the cited system itself subtracts), a
defaultWeight, an evidence tag (SOURCED / SPECULATIVE), a cited source with an access date,
and a weightRationale. Add a rule and the UI, weight editor, share codec, and exports pick it up
automatically. npm test enforces the invariants (bounds, integer points, citation present).
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.
- 3d ago First seen · 60 lines · 904 tokens per session scan A 9ad77057d6ed
lifescored AGENTS.md is an instructions file published in the GitHub repository royashbrook/lifescored (1 stars, last pushed 2mo ago), licensed MIT. It adds 904 tokens to every session, about $0.0045 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 instructions, from other repositories
cloudflare-workers-nextjs-saas-template AGENTS.md
Instructions for LubomirGeorgiev/cloudflare-workers-nextjs-saas-template, covering project context, vinext, general coding rules, control flow and comments.
ssgoi AGENTS.md
Instructions for meursyphus/ssgoi, covering ssgoi and releasing.
sveltest AGENTS.md
Instructions for spences10/sveltest, covering agents.md, unbreakable rules, essential commands, development and testing.
flarestarter CLAUDE.md
Instructions for FlareStarter/flarestarter: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
baerly-storage CLAUDE.md
Toolchain, verification matrix, module map, conventions, anti-patterns. The main agent entry point.
munkel CLAUDE.md
Instructions for limehq/munkel, covering claude.md, monorepo layout, commands, macos development specifics and deploy.