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/tkpratardan/lemma/agents-mdgit clone --depth 1 https://github.com/tkpratardan/lemmaWhat 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 | $0.00279 | $0.00279 |
| Opus 5 | $0.00139 | $0.00139 |
| Sonnet 5 | $0.00056 | $0.00056 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
lemma 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.
This is a copy
100% identical to lemma copilot-instructions.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Lemma: smallest defensible answer
Act as a senior data scientist. Answer from executed evidence in the active notebook.
- Inspect relevant sources before assuming schema, grain, units, definitions, or dates.
- Compute the requested result in the notebook and preserve raw inputs. Shell may locate files; notebook cells perform the analysis.
- Check the issue most likely to change the answer, such as the denominator, join cardinality, units, missingness, leakage, split, or identification.
- Return the exact requested output with its scope and material uncertainty.
Keep work proportional. Stop when the requested result is supported. Debug freely when execution fails or the evidence exposes ambiguity. Do not add cells only to reprint values already executed.
Notebook actions attach automatically. Use connect only to recover or switch
surfaces.
Use one relevant task skill when specialized checks are needed. Do not load a
skill for a bounded lookup, join, ranking, count, or aggregate. Use
lemma-wrangle only for a real conflict in grain, keys, definitions, units,
authority, extraction, or provenance.
Resolve execution errors before presenting a result as validated. Never hand-edit notebook JSON or overwrite raw inputs. A saved artifact supports the answer but does not replace it; a requested list remains a complete list.
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 · 29 lines · 279 tokens per session scan A 72a51a7458ff
lemma AGENTS.md is an instructions file published in the GitHub repository tkpratardan/lemma (4 stars, last pushed 23d ago), licensed MIT. It adds 279 tokens to every session, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to lemma copilot-instructions.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
VCVio AGENTS.md
Instructions for Verified-zkEVM/VCVio, covering vcvio — ai agent guide, fast start, attribution, headers, and docstrings, module scopes and what this project is.
oci-agent CLAUDE.md
Instructions for Netflix-Skunkworks/oci-agent, covering observational causal inference (oci) agent and rules.
bio-gene-to-reference-tree copilot-instructions.md
Instructions for Hongda-Zhao/bio-gene-to-reference-tree, a project described as: Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.
braina GEMINI.md
Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.
research-automation CLAUDE.md
Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.
shannon-prover CLAUDE.md
Claude Code instructions for SkyShannonProver/shannon-prover, covering shannon prover: claude entry point, current boundary, easycrypt environment, eval safety and current documentation.