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 primeline-ai/kairn --skill kairn-memorygit clone --depth 1 https://github.com/primeline-ai/kairnWrote 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/primeline-ai/kairn/kairn-memory)<a href="https://agentmods.dev/skills/primeline-ai/kairn/kairn-memory"><img src="https://agentmods.dev/badge/skills/primeline-ai/kairn/kairn-memory/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/primeline-ai/kairn/kairn-memory"><img src="https://agentmods.dev/badge/skills/primeline-ai/kairn/kairn-memory.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 | $0.00032 | $0.00256 |
| Opus 5.5 | $0.00013 | $0.00102 |
| Sonnet 5.5 | $0.00006 | $0.00051 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
kairn-memory 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 4d 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.
What it actually says
Recall before acting: call kn_recall(topic="<project and topic>") before
starting work or choosing an approach. Use relevant past knowledge; an empty
result means nothing was found for that topic.
Save after learning: call kn_learn(content="<what was learned>", type="solution", confidence="high") after a useful fix or decision.
Choose type from decision, pattern, solution, workaround, gotcha,
or preference. Use confidence high for permanent knowledge, medium for
likely conclusions, and low for exploratory findings. Include enough
context to make the entry useful later.
Use kn_context(keywords="<topic>") for related graph context,
kn_memories(text="<query>") to search saved experiences, and kn_status()
to inspect the store.
Never save secrets, credentials, or personal data. The store lives in
~/.kairn on this machine; what you recall is sent to the model as part of
the conversation.
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.
- 4d ago First seen · 24 lines · 32 tokens per session scan A e50241d6e20b
kairn-memory is a skill published in the GitHub repository primeline-ai/kairn (13 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 256 once invoked, about $0.0001 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 2026-10-12.
Other skills, from other repositories
kg-maintain
Knowledge graph maintenance — a bounded, resumable pass that pays down the graph's DEBT line (rendered after HEALTH in every kgread). Run it when invoked, when DEBT shows HIGH, or as a dispatched maintenance subagent. The same work also arrives in a smaller shape: a CHORE, one category and one or two named targets…
kg-scout
Mine Claude Code and Codex conversation history for patterns and insights worth preserving.
kg-core
Knowledge Graph — persistent, granular, evolving memory. Part of memory initially arrives preloaded: a "KG MEMORY PRELOADED" block carrying the sessionid and most important portion of memory. Then the full read is on you: kgread(cwd=" ") comes before any work, whatever the task. Full read still brings up only most…
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
forgetful-entities
Model the things knowledge attaches to — people, organisations, devices, products, system components. Use when a new thing surfaces that memories will reference, when relationships between things need recording (owns, depends on, part of), or when another skill routes a pointable thing here. Litmus: an entity is a…
forgetful-explore
Explore the Forgetful knowledge graph when flat search isn't enough — cross-project investigations, "what do we know about X", entity-centred questions, tracing how decisions connect. Use when recall returns fragments that reference entities or trail across domains. Walks memories, entities, and relationships into one…