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 AnthonyAlcaraz/agentic-graph-rag-skills --skill bi-temporal-edgegit clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-skillsWrote 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/anthonyalcaraz/agentic-graph-rag-skills/bi-temporal-edge)<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/bi-temporal-edge"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/bi-temporal-edge/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/anthonyalcaraz/agentic-graph-rag-skills/bi-temporal-edge"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/bi-temporal-edge.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 | $0.00193 | $0.02755 |
| Opus 5 | $0.00097 | $0.01378 |
| Sonnet 5 | $0.00039 | $0.00551 |
| Haiku 4.5 | $0.00019 | $0.00276 |
Grade A, and why
bi-temporal-edge 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bi-Temporal Edge
Overview
Agent memory that overwrites facts in place loses the historical trace that
makes incident reconstruction possible. The DevOps running example from
Ch5/Ch6 makes this concrete: the checkout API had its EC2 instance type
changed from t3.large to m5.xlarge on 2026-03-10. The outage occurred
2026-03-15T08:00Z. By the time the post-mortem starts, the configuration
store says m5.xlarge — but the agent investigating the outage needs to
know what the config was at the time of the outage, not what it is now.
The bi-temporal edge tracks two times per relationship:
- Validity time (
valid_from,valid_until): when the fact was true in the domain.valid_until=Nonemeans currently valid. - Ingestion time (
ingested_at): when the system learned about the fact. May be days or weeks after the fact became true.
These two dimensions are independent. A fact can be valid-but-not-yet-known (staging update pushed to prod 2026-03-10 but only logged 2026-03-12), or known-but-no-longer-valid (we recorded it 2026-03-10, invalidated 2026-03-15 when the rollback happened). Both are common in production.
Once edges carry both timestamps, three new query primitives become
mechanical: was_valid_at(timestamp) answers point-in-time, history(node)
answers full-evolution, ingestion_lag(edge) answers debugging-the-debugger
("was our agent acting on stale data when it made that decision?").
The chapter pairs this with HINDSIGHT's typed-link extension: each edge
carries a link_type ({entity, semantic, temporal, causal}) and a weight
multiplier for graph traversal. During spreading-activation search, causal
and entity links get μ > 1; weak semantic or long-range temporal links get
μ ≤ 1. This biases the agent's reasoning toward explanatory connections.
When to Use
Trigger contexts:
- DevOps incident reconstruction — what was the config at outage time?
- Audit-grade question — "What did the agent know on 2026-03-15 when it recommended X?"
- Regulated environment — compliance evidence needs reproducible point-in- time queries.
- Multi-agent memory where Agent A wrote a fact, Agent B needs to know whether the fact was valid when Agent A wrote it.
What ships with it
3 files 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.
- 11d ago First seen · 171 lines · 193 tokens per session scan A bfe6183e9b56
bi-temporal-edge is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 193 tokens to every session and 2,755 once invoked, about $0.0010 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
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…
library
Sync agent memory files to a Cortex knowledge graph for enhanced retrieval, hybrid search (vector + keyword + graph), AI-powered Q&A with agentic deep research, and knowledge graph exploration.
openclaw
Persistent memory for agents. Stores preferences, decisions, facts, and events as a connected knowledge graph. Recalled by who, what, when, or why.
graph-ask
Ask any natural language question about the memory graph. You generate Cypher directly and execute it. Use when the user has a complex or ad-hoc question that the standard graph tools don't cover.
ingest-audio
Transcribe a local audio or video file using Whisper and ingest it into the memory graph. Use when the user has a local MP3, WAV, M4A, MP4, or similar audio/video file they want to add to their knowledge graph.
ingest
Ingest a file or URL into the memory graph. Handles local files (text, PDF, DOCX, XLSX, images, etc.) and URLs (web pages, YouTube, Wikipedia, RSS). Use when the user wants to add any document or web content to their knowledge graph.