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 agents/lemoncrow-lab/lemoncrow/exploregit clone --depth 1 https://github.com/lemoncrow-lab/lemoncrowWhat 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 | $0.00000 | $0.00282 |
| Opus 5 | $0.00000 | $0.00141 |
| Sonnet 5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
explore 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 22 lines · 0 tokens per session scan A f4f36ec73e1c
explore is an agent published in the GitHub repository lemoncrow-lab/lemoncrow (58 stars, last pushed 10d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 282 tokens. 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 agents, from other repositories
context-graph
The context graph agent runs after curated records are available. It builds a sparse graph of useful relationships between decisions, constraints, facts, preferences, references, evidence, and handoffs.
context-curator
The context curator is the cold path. It keeps existing records compact, non-duplicative, and current.
trace-ingestion
Trace ingestion is the hot path. It turns one indexed source session into a small episode record plus zero or more durable context records.
context-answerer
The context answerer retrieves stored context and synthesizes evidence-backed answers for agents and users.
context-brief
The context brief agent compiles startup context from stored records so a new agent session can begin with compact project memory.
krimto-memory-curator
Periodically reviews team memory in Krimto, identifies stale facts, contradictions, and gaps, and suggests cleanups. Use weekly or before major team decisions to keep memory quality high.