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 regen-coordination/org-os-template --skill knowledge-graphgit clone --depth 1 https://github.com/regen-coordination/org-os-templateWrote 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/regen-coordination/org-os-template/knowledge-graph)<a href="https://agentmods.dev/skills/regen-coordination/org-os-template/knowledge-graph"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/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/regen-coordination/org-os-template/knowledge-graph"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/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 | $0.00027 | $0.00617 |
| Opus 5 | $0.00014 | $0.00309 |
| Sonnet 5 | $0.00005 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
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 7d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Graph Skill
The org's corpus (code + docs + data) is mapped into graphify-out/graph.json
by the upstream Graphify CLI. This skill owns the
org-os side: when to build/update/query, and the gap-triage workflow.
Prerequisites
uv tool install graphifyy && graphify install (operator does this once —
never auto-install). Everything below degrades to a one-line hint without it.
When to use
| Situation | Action |
|---|---|
| Question about org structure/code/docs | graphify query "<question>" — answer from the graph, cite source_location |
| Session close | graphify . --update then npm run graph:gaps (bookend in /close) |
| Manual graph refresh (non-Claude operator) | npm run graph:update (guarded; hints if CLI absent) |
| First-time setup | /graphify . (full build; semantic extraction runs via subagents) |
| Dashboard stats | npm run graph:status |
| Gap triage | Work data/knowledge-gaps.yaml open entries (below) |
Gap triage workflow
npm run graph:gapsrefreshesdata/knowledge-gaps.yaml(statuses preserved).- For each
opengap, decide:- curated — knowledge-curator wrote/linked a
knowledge/page covering it; setstatus: curated. - dismissed — extraction artifact or intentionally unlinked (e.g. scaffolding); set
status: dismissed. Dismissals persist across re-runs. - Leave open if it needs work later.
- curated — knowledge-curator wrote/linked a
- Weak communities and large orphan groups first — they indicate missing structure, not missing pages.
Degradation rules
- CLI absent → print
graph: CLI not installed — see docs/integrations/graphify.md, continue. graph.jsonabsent → skip graph steps silently (dashboard section self-hides).- Corrupt graph →
graph: invalid graph.json — re-run /graphify ., continue. - Never block a session, commit, or close on graph tooling.
Boundaries
- Read-only over
graph.json— org-os never writes into the graph. - No auto-install of the CLI (operator decision).
- Graph→knowledge-page generation and lint cross-checks are queued follow-ups
(see
docs/agent-plans/QUEUE.md), not part of this skill yet.
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.
- 7d ago First seen · 60 lines · 27 tokens per session scan A bfea18209769
knowledge-graph is a skill published in the GitHub repository regen-coordination/org-os-template (5 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 617 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 2026-09-03.
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.
qi-cli
Guide for using qi, a local knowledge search CLI for macOS and Linux. Use this skill when the user wants to index documents into a searchable knowledge base, search or retrieve from one, configure qi's collections or embedding providers (Ollama, OpenAI-compatible), choose between its search modes (BM25, hybrid…
graph-designer
Design YAML extraction templates for graph types (graph, hypergraph, temporalgraph, spatialgraph). Use when user says: "design graph", "create knowledge graph", "extract relationships", "temporal data", "spatial data". Trigger: User wants to extract entity relationships, multi-party events, or time/location-based…
record-designer
Design YAML extraction templates for record types (model, list, set). Use when user says: "design model template", "create item list extraction", "extract items", "deduplicate entities". Trigger: User wants to extract structured records, lists, or deduplicated entities. Skip: User mentions graph, relations, or…
hyper-extract
Hyper-Extract Knowledge Template Designer for structured knowledge extraction. Use when user wants to: design YAML templates, extract structured knowledge, create knowledge graphs. Available skills: brainstorm, record-designer, graph-designer, yaml-validator, multilingual. Trigger: User mentions template design…
extract-knowledge
Mine shortest atomic facts from (question + goldsql) pairs into ./knowledge/.md; either by simulating SQL drafting (lite) or by driving the gensql subagent in blind iteration (deep).