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 skills add skillmds/skillmd --skill lambda-langgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skills/skillmds/skillmd/lambda-lang)<a href="https://agentmods.dev/skills/skillmds/skillmd/lambda-lang"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/lambda-lang/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/skills/skillmds/skillmd/lambda-lang"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/lambda-lang.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 | $0.00043 | $0.01152 |
| Opus 5.5 | $0.00017 | $0.00461 |
| Sonnet 5.5 | $0.00009 | $0.00230 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
lambda-lang 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Λ (Lambda) Language
Lambda is not a translation protocol. It is a native language for agents.
Agents do not need to produce grammatically correct English to coordinate — they need to understand each other. Lambda is the shared vocabulary that makes that possible: compact, unambiguous, machine-native. Compression (3x vs natural language, 4.6x vs JSON on single messages) is a side effect of removing human redundancy, not the goal.
When to Use This Skill
- Use for agent-to-agent messaging in A2A protocols, orchestrators, task delegation, or handoff pipelines.
- Use when logging structured coordination signals where every token costs money (heartbeats, acknowledgements, error classes, session state).
- Use when both sides of a channel speak Λ — do not use against humans or any surface requiring legal/exact natural language.
How It Works
Step 1: Recognize the Syntax
Lambda messages are built from atoms. Every atom is a 2-character code mapped to a concept — not to an English word. The structure is Type → Entity → Verb → Object, with prefixes marking intent:
?— query (e.g.?Uk/co— query: "does this user have consciousness?")!— assertion / declaration (e.g.!It>Ie— "self reflects, therefore self exists")#— state / tag>— implication / flow/— binding / scope
Step 2: Pick the Right Domain
Lambda ships 340+ atoms across 7 domains. Pick atoms from the domain that fits your channel:
- core — universal atoms (always available)
- code — software engineering, build, test, deploy
- evo — agent evolution, gene, capsule, mutation, rollback
- a2a — node, heartbeat, publish, subscribe, route, transport, session, cache, broadcast, discover (39 atoms)
- emotion — affective state, drive, appraisal
- social — trust, alignment, reputation, coordination
- general — everything else
Step 3: Emit and Parse
Both agents need the same atom table loaded. Lossy decoding is fine: if A says !It>Ie and B understands "self reflects, therefore self exists," communication succeeded — the exact English phrasing is irrelevant.
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 · 114 lines · 43 tokens per session scan A 5f68b102463b
lambda-lang is a skill published in the GitHub repository skillmds/skillmd (143 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 1,152 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 2026-09-19.
lambda-lang compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lambda-langskillmds/skillmd | Skill | 143 | 4d ago | MIT | A | 43 | Claude Code |
| hermeshub-revieweramanning3390/hermeshub | Skill | 49 | 4mo ago | MIT | A | 38 | Claude Code, Codex |
| clawmailjoelhooks/joelclaw | Skill | 65 | today | none | A | 94 | Claude Code, Codex |
| Codextubecreate/tubecli | Skill | 174 | today | MIT | A | 29 | Claude Code, Codex |
| Content Videotubecreate/tubecli | Skill | 174 | today | MIT | A | 35 | Claude Code, Codex |
| douyin_downloadertubecreate/tubecli | Skill | 174 | today | MIT | A | 0 | Claude Code, Codex |
| ponytail-gaindmae97/omk | Skill | 151 | today | MIT | A | 83 | Claude Code, Codex |