Borrowing it
Nothing to install: this file belongs to AsiaOstrich/EngramGraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AsiaOstrich/EngramGraph/main/.agents/skills/knowledge-graph/SKILL.mdgit clone --depth 1 https://github.com/AsiaOstrich/EngramGraphWrote 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/asiaostrich/engramgraph/knowledge-graph)<a href="https://agentmods.dev/skills/asiaostrich/engramgraph/knowledge-graph"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/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/asiaostrich/engramgraph/knowledge-graph"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/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 | $0.00124 | $0.00981 |
| Opus 5.5 | $0.00050 | $0.00392 |
| Sonnet 5.5 | $0.00025 | $0.00196 |
| Haiku 4.5 | $0.00012 | $0.00098 |
Grade A, and why
knowledge-graph scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Glob, Grep, Bash(curl:*) How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Graph | 知識圖
Language: English | 繁體中文
Answer structural questions across specs, decisions, and code — "what is the full impact chain of XSPEC-205?" — using the Knowledge Graph Memory relationship schema. Works with or without a graph engine.
回答橫跨規格、決策與程式碼的結構性問題——「XSPEC-205 的完整影響鏈是什麼？」——依據知識圖記憶標準的關係 schema。有無圖引擎皆可運作。
Implements: XSPEC-237 Phase 5 — knowledge-graph skill (EngramGraph opt-in)
Mode Selection | 模式選擇
Detect which mode to use before answering:
| Condition | Mode |
|---|---|
ENGRAM_URL set, or a local graph engine responds on /health |
Service mode (engine) |
| Otherwise | Degraded mode (Markdown) |
Workflow | 工作流程
- Resolve the target — normalise the argument to a canonical id (
XSPEC-205,DEC-062, a function name). - Choose mode — probe for a graph engine (service) else fall back (degraded).
- Service mode (AC-5b) — issue a single multi-hop query and present the returned chain, including cross-domain links (code → spec → decision):
curl -s -X POST "$ENGRAM_URL/graph/impact-analysis" \ -H 'content-type: application/json' \ -d '{"nodeId":"XSPEC-205","maxHops":3}' - Degraded mode (AC-5a) — with no engine, read the target document, follow its
impacts/impacted_by/supersedes/relatedfront-matter and inline[[ref]]links by reading the linked files, and assemble the chain manually (bounded by reading depth). - Present the chain — list the connected Specs and Decisions, the edge type for each hop, and (if present) each node's
confidence, highest first. - State the mode used — always say whether the answer came from the engine or Markdown fallback, so completeness is clear.
Relationship Schema | 關係 schema
See knowledge-graph-memory. Front-matter fields: related, impacts, impacted_by, supersedes, implements. Edge derivation: Decision impacts Spec → IMPACTS; Decision supersedes Decision → SUPERSEDES.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 14d ago First seen · 63 lines · 124 tokens per session scan A 8ea55a971896
knowledge-graph is a skill published in the GitHub repository AsiaOstrich/EngramGraph (3 stars, last pushed today), licensed MIT. It adds 124 tokens to every session and 981 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
mushroom
Live graph memory for agents — query and create entities, derive relationships by rule, explain why two things are associated, read the graph at a past commit, ask what a change would do, and answer as one role. Trigger on: memory, remember, recall, relationship, entity, association, why are X and Y related, as of…
omnigraph
Operate OmniGraph graphs and deployments. Use for .pg schemas, .gq queries, OmniGraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema…
kivgraph
Use Kivgraph's local MCP server to search symbols, read their source, and follow references, dependencies, cross-repository consumers and graph status in the indexed code graph.
openclaw
Persistent memory for agents. Stores preferences, decisions, facts, and events as a connected knowledge graph. Recalled by who, what, when, or why.
brain-dream
Brain maintenance -- replay conversations, fix graph quality, surface signals.
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.