Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gl00mt1t4n/loom-kgnpx agentmods add skills/gl00mt1t4n/loom-kg/personal-knowledge-graphWrote 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/gl00mt1t4n/loom-kg/personal-knowledge-graph)<a href="https://agentmods.dev/skills/gl00mt1t4n/loom-kg/personal-knowledge-graph"><img src="https://agentmods.dev/badge/skills/gl00mt1t4n/loom-kg/personal-knowledge-graph/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/gl00mt1t4n/loom-kg/personal-knowledge-graph"><img src="https://agentmods.dev/badge/skills/gl00mt1t4n/loom-kg/personal-knowledge-graph.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 | $0.00019 | $0.00532 |
| Opus 5 | $0.00010 | $0.00266 |
| Sonnet 5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
personal-knowledge-graph 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 9d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Knowledge Graph
Use for Obsidian KG changes, durable knowledge, graph/index rules, task-vs-note routing, tombstones, templates, validation, and skill provenance.
Constants to resolve per vault
- Vault root: current LoomKG vault root
- Root index:
Root Index.mdunless customized - Architecture:
Graph Architecture.md - Properties:
Registries/Properties.md - Tags:
Registries/Tags.md - External corpora: user-approved detached folders only
Routing
- Tasks/status/follow-up -> user's task system, if any.
- Durable reasoning/context/evidence -> Obsidian.
- Both -> update both and link when useful.
Graph invariants
- Every normal non-external markdown file must be reachable from the root index.
- One primary home per note; use tags/links for cross-domain overlap.
- No duplicate notes across domains.
- Domain folders are for browsing; frontmatter is semantic truth.
- External corpora may be cited, but they do not define this graph's taxonomy or purpose.
Templates
- Use
Templates/when creating new KG notes. - Remove optional placeholder fields that are not useful.
- Do not create blank note shells; create/update only when there is durable content.
Write workflow
- Search existing notes.
- Read relevant maps/links.
- Prefer updating existing nodes.
- Create only distinct durable notes.
- Use controlled properties/tags from registries.
- Use the closest template, then remove unused optional fields.
- Link sparsely but enough for reachability.
- Tombstone/supersede stale reasoning instead of deleting it.
Validation
Run from vault root after edits:
python scripts/validate_vault.py .
Git policy
For approved vault changes: verify, run git status --short, commit related changes, push to the user's origin/main, and report the commit hash.
When a commit is pushed, end with a concise line like: commit abc1234: "Message" pushed to main.
Done means
- search-before-write done;
- external corpora untouched unless explicitly requested;
- no unresolved wikilinks;
- all normal markdown reachable from root index;
- validation passed;
- approved changes committed/pushed;
- useful completed work considered for Obsidian/task capture, with user asked before creating entries.
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.
- 9d ago First seen · 74 lines · 19 tokens per session scan A 511dbbedaf6c
personal-knowledge-graph is a skill published in the GitHub repository gl00mt1t4n/loom-kg (5 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 532 once invoked, about $0.0001 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
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.
mind
Local project memory with recall, provenance, policy, and dreams.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
engraphis-memory
Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
memory-proactive
Proactive layered recall and generic domain-aware routing.