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 hindsight-epistemic-classifiergit 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/hindsight-epistemic-classifier)<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/hindsight-epistemic-classifier"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/hindsight-epistemic-classifier/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/hindsight-epistemic-classifier"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/hindsight-epistemic-classifier.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 | $0.00160 | $0.01848 |
| Opus 5 | $0.00080 | $0.00924 |
| Sonnet 5 | $0.00032 | $0.00370 |
| Haiku 4.5 | $0.00016 | $0.00185 |
Grade A, and why
hindsight-epistemic-classifier 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HINDSIGHT 4-Network Epistemic Classifier
Overview
Production memory systems benefit from distinguishing what the agent observed from what it believes. HINDSIGHT (Latimer et al., 2025, cited in Ch4) organizes memory into four networks:
- World network — objective facts about external reality. Verifiable by external sources (the production region is us-east-1, the CEO of ACME is X, the API endpoint returned 503).
- Experience network — the agent's own first-person actions. "I called the deploy API at 22:30." "I retrieved 5 documents." First-person, timestamped, agent-as-actor.
- Opinion network — subjective beliefs with confidence scores. "I believe the root cause is X with 0.7 confidence." Inference, not observation.
- Observation network — synthesized entity summaries. "Sarah is the on-call lead this week" derived from the union of {Sarah's calendar, on-call rotation doc, prior incidents}. Distillation, not evidence.
Per the HINDSIGHT paper as quoted in Ch4: "developers and users can see what the agent knows versus what it believes." This skill is the classification layer that makes the distinction queryable.
When to Use
- Audit-grade agents — when a user asks "how do you know that," the response must trace evidence to network
- Regulated environments — opinion must be flagged as opinion, not stated as fact
- Multi-agent systems — Agent A's opinion should not become Agent B's fact via uncritical knowledge sharing
- Debugging hallucinations — if the agent stated X confidently, the network classification tells you whether X is evidence-grounded (World/Experience) or inference (Opinion/Observation)
Phrases: "where did the agent get this", "is this fact or inference", "justify the answer", "trust calibration", "HINDSIGHT", "epistemic status".
When NOT to Use
- One-shot agents that need no justification trail
- Storage-only systems (the classification is for retrieval-time reasoning, not just persistence)
- Pure-retrieval agents that never synthesize — the Observation network is empty, the Opinion network is empty; just use World + Experience
What ships with it
2 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 · 141 lines · 160 tokens per session scan A ba55f40b64de
hindsight-epistemic-classifier is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 160 tokens to every session and 1,848 once invoked, about $0.0008 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.