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/dcroote/lambs/agents-mdgit clone --depth 1 https://github.com/dcroote/lambsWhat 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 | $0.01793 | $0.01793 |
| Opus 5 | $0.00897 | $0.00897 |
| Sonnet 5 | $0.00359 | $0.00359 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
lambs 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 2d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LAMBS — guide for AI agents
This file serves two audiences. Jump to the section that matches the task.
| If you are… | Read |
|---|---|
| Using LAMBS to analyze antibody sequences (VH/VL, basket, liabilities, germline) | Using LAMBS (analysis agents) |
Changing LAMBS (bugs, features, tests, germline DB, UI in index.html) |
Developing LAMBS (contributor agents) |
Product rule (both audiences): end users and analysis agents rely on one offline index.html. Do not introduce a second runtime artifact, npm install for users, or a parallel analysis implementation.
Using LAMBS (analysis agents)
Your job is to run analysis and consume structured results, not to edit the repo or reimplement algorithms.
How to run analysis
- Open
index.htmlin a browser (file URL or static server). - Prefer
window.LAMBSover scraping the DOM.
| Method | Returns |
|---|---|
LAMBS.analyzeMabReportFromRaw(vhRaw, vlRaw) |
{ ok, report? | errors? } — preferred |
LAMBS.analyzeSingle(vhRaw, vlRaw) |
Report object, or { ok: false, errors } on validation failure |
LAMBS.analyzeMabReport(vhSeq, vlSeq) |
Report from cleaned AA strings |
LAMBS.buildChainReport(varSeq, 'VH' | 'VL') |
Variable-region chain report |
LAMBS.buildClusterReport(basket, threshold, filterNames) |
Cluster report |
LAMBS.getHumanIgGEuNumbers(isotype) |
Eu index array for IGHG1–IGHG4, else null (IMGT Hu_IGHGnber) |
LAMBS.mapEuOntoConstantAlignment(aligned2, species, isotype) |
Per-column Eu numbers for a CH alignment, or null |
LAMBS.lambsReportToJSON(report) |
JSON string (no _constMatch / alignment blobs) |
LAMBS.lastReport |
Last single-tab report after Analyze |
LAMBS.lastClusterReport |
Last cluster report after Cluster & Analyze |
Playwright / browser MCP:
await page.goto('file:///path/to/index.html');
const result = await page.evaluate((vh, vl) => LAMBS.analyzeMabReportFromRaw(vh, vl), vhRaw, vlRaw);
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.
- 2d ago First seen · 155 lines · 1,793 tokens per session scan A 1ceb5ad6b619
lambs AGENTS.md is an instructions file published in the GitHub repository dcroote/lambs (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,793 tokens to every session, about $0.0090 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 2026-08-30.
Other instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
spring-ai-agentcore AGENTS.md
Instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
agentoscope AGENTS.md
Instructions for rafaelcg/agentoscope, covering agentoscope — agent instructions, what this is, layout, commands and conventions.