OpenLore is a shared knowledge repository that stores agent context as ordinary Markdown files and makes the same files available to agents, people, and jobs through interfaces such as shell access, web view, and MCP. It is for teams using several agents or repositories that need current, inspectable knowledge with controlled read and write access. The catalogue skills help agents use and manage this repository.
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 aakarim/OpenLore --skill openlore-housekeepinggit clone --depth 1 https://github.com/aakarim/OpenLoreWrote 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/aakarim/openlore/openlore-housekeeping)<a href="https://agentmods.dev/skills/aakarim/openlore/openlore-housekeeping"><img src="https://agentmods.dev/badge/skills/aakarim/openlore/openlore-housekeeping/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/aakarim/openlore/openlore-housekeeping"><img src="https://agentmods.dev/badge/skills/aakarim/openlore/openlore-housekeeping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00873 |
| Opus 5.5 | $0.00019 | $0.00349 |
| Sonnet 5.5 | $0.00010 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
openlore-housekeeping 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 11d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenLore Housekeeping
Keep a shared knowledge repository healthy. Run each check below, collect findings,
and publish one report. Requires the openlore skill (server access via
$OPENLORE_SSH).{{if .Mounts}} Documentation is mounted at {{range $i, $m := .Mounts}}{{if $i}}, {{end}}{{$m}}{{end}};
the checks below target {{.Mount}} — repeat them for each mount.{{end}}
Find stale documents
Documents carry frontmatter. Use lore meta to list paths with dates, then
flag old ones:
ssh $OPENLORE_SSH "lore meta {{.Mount}} | jq -r 'select(.updated != null) | [.updated, .path] | @tsv' | sort"
Flag anything older than the agreed threshold (default: 90 days). Also flag documents with no frontmatter date at all:
ssh $OPENLORE_SSH "lore meta {{.Mount}} | jq -r 'select(.updated == null) | .path'"
Find broken internal links
Extract relative Markdown links and check each target exists:
ssh $OPENLORE_SSH "grep -rho ']([^)h][^)]*)' {{.Mount}} | tr -d ']()' | sort -u"
For each path, test it: ssh $OPENLORE_SSH "test -e {{sub .Mount "<target>"}} || echo missing: <target>".
Check the publish inboxes
Items published into an inbox wait for a human to move them into the docset. List what is waiting and how old it is:
ssh $OPENLORE_SSH "find / -type f | grep '/inbox/' | xargs -I{} stat {}"
Flag inbox items older than 7 days: they are stuck and need a human decision.
{{if exists "/trajectories"}}## Check trajectory freshness
This server has a /trajectories docset. Confirm recent agent runs are being
synced (ls -l shows modification times):
ssh $OPENLORE_SSH "ls -l /trajectories"
Compare with local ~/.headlong/trajectories/. Sync any completed run that is
missing (see the openlore skill for the sync procedure).
{{end}}{{if exists "/skills"}}## Check skill coverage
This server hosts a /skills collection. Verify every skill directory has a
SKILL.md:
ssh $OPENLORE_SSH "ls /skills | while read -r d; do test -e /skills/\$d/SKILL.md || echo missing: \$d; done"
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.
- 11d ago Changed · +7 lines 2cb44914ff88
- 13d ago Changed 3e0ed092096b
- 1mo ago First seen · 86 lines · 48 tokens per session scan A 2653fe7f9fd2
openlore-housekeeping is a skill published in the GitHub repository aakarim/OpenLore (1,561 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 873 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 2026-08-30.
Other skills, from other repositories
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
Memory Context Recall
Recall past conversations and facts from agent memory.
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.