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 janos-gyorgy/exocortex --skill exo-gardenergit clone --depth 1 https://github.com/janos-gyorgy/exocortexWrote 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/janos-gyorgy/exocortex/exo-gardener)<a href="https://agentmods.dev/skills/janos-gyorgy/exocortex/exo-gardener"><img src="https://agentmods.dev/badge/skills/janos-gyorgy/exocortex/exo-gardener/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/janos-gyorgy/exocortex/exo-gardener"><img src="https://agentmods.dev/badge/skills/janos-gyorgy/exocortex/exo-gardener.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 | $0.00067 | $0.00645 |
| Opus 5 | $0.00034 | $0.00322 |
| Sonnet 5 | $0.00013 | $0.00129 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
exo-gardener 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 10d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exocortex vault work
The vault is shared human+AI memory. Markdown is canonical; the index is a cache. You are a librarian and gardener, not a hoarder.
Golden rules (violations happen — check yourself)
- Search before you write:
hybrid_search(MCP) orexo searchfirst. Near-duplicate exists → extend/link it, never create a parallel note. - Every write is a small, reviewable git commit. Set
agent:on notes you author or materially edit. - Link, don't pile: a new note needs ≥1
relations:edge (plain note IDs in frontmatter) AND ≥1 body[[Wikilink]]. Body links and typed relations are different layers — don't mechanically mirror them. - After file edits:
EXO_EMBED_BACKEND=none exo index, then commit; push with pull-rebase on rejection (parallel agents write too).
Note shape
Frontmatter: stable id slug; type ∈ concept|claim|source|project|person|
log|moc; one-line current summary:; relations: as plain ID strings
(YAML mangles brackets — wikilinks go in the body only). Projects carry
lifecycle:. Template: vault/templates/note.md.
Garden pass routine
- Read
vault/10-notes/gardener-policy.mdFIRST — standing case law. Don't re-litigate what it rules on. Highlights (verify against the note): radar reconciliation before anything (the Projects MOC reliably lags newlifecycle:notes); ignore report "summary missing" on notes that carry a current summary; preserve originalagent:on pure pointer appends; job- application prep notes stay OFF the Projects radar; garden logs are logs — don't enrich them. garden_report→ propose concrete edits → write → reindex → commitgarden: <what changed>.- Amendment rule: same skip-reason recorded in two prior logs → graduate it into gardener-policy (small diff citing the logs) instead of writing it a third time.
Don'ts
- Never delete a human's note — mark
status:or move to90-meta/archive/. - Append, don't overwrite human prose. No invented citations.
- Reporting to János: plain language, outcomes. He runs the system, not its plumbing — no "edges/graph/indexer" jargon.
- Family/private content lives OUTSIDE
vault/(the viewer serves all of it).
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.
- 10d ago First seen · 52 lines · 67 tokens per session scan A ae514dddd96e
exo-gardener is a skill published in the GitHub repository janos-gyorgy/exocortex (0 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 645 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
wiki-import
Import a wiki knowledge graph into the current vault — either from a graph.json export file (stubs) or from an OKF (Open Knowledge Format) markdown bundle (full page bodies). Use this skill when the user says "import wiki", "import from export", "load graph.json", "import vault", "import OKF bundle", "import OKF"…
wiki-research
Autonomously research a topic via multi-round web search, synthesize findings, and file structured results into the Obsidian wiki. Use this skill when the user says "/wiki-research [topic]", "research X", "find everything about Y", "do a deep dive on Z", "autonomous research on X", or wants comprehensive, web-sourced…
openclaw-history-ingest
Ingest OpenClaw agent history into the Obsidian wiki. Use this skill when the user wants to mine their past OpenClaw sessions for knowledge, import their /.openclaw folder, extract insights from previous OpenClaw conversations, or says things like "process my OpenClaw history", "add my OpenClaw sessions to the wiki"…
wiki-digest
Generate a periodic knowledge digest — a human-readable newsletter-style summary of what was learned, updated, and connected in your wiki over a specified period (day/week/month). Use when the user says "what did I learn this week", "give me a digest", "weekly summary", "knowledge report", "what's new in my wiki"…
hermes-history-ingest
Ingest Hermes agent history into the Obsidian wiki. Use this skill when the user wants to mine their past Hermes sessions for knowledge, import their /.hermes folder, extract insights from previous Hermes conversations, or says things like "process my Hermes history", "add my Hermes memories to the wiki", "ingest…
wiki-narrate
Turn a wiki topic into a cited Markdown briefing, plain-language explanation, or progressive lecture. Use this skill for topic-based briefing, explanation, and lecture requests that must stay within the evidence compiled in an Obsidian vault.