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 EmpiricaAI/empirica --skill epistemic-editinggit clone --depth 1 https://github.com/EmpiricaAI/empiricaWrote 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/empiricaai/empirica/epistemic-editing)<a href="https://agentmods.dev/skills/empiricaai/empirica/epistemic-editing"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/epistemic-editing/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/empiricaai/empirica/epistemic-editing"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/epistemic-editing.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 | $0.00216 | $0.02159 |
| Opus 5.5 | $0.00086 | $0.00864 |
| Sonnet 5.5 | $0.00043 | $0.00432 |
| Haiku 4.5 | $0.00022 | $0.00216 |
Grade A, and why
epistemic-editing 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 1mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epistemic editing
A document is a pile of claims. Most review looks at the prose. This looks at the claims: what each one rests on, whether anyone checked, and what happens if it is wrong.
The output is not a marked-up draft. It is a galley: the document rendered in full with a flag at each paragraph that needs a decision, each flag carrying its evidence and a proposed edit, and a decision recorded per flag. Nothing is rewritten silently — the author decides, and the accepted set drives a versioned change.
The one rule
Every flag states how it was grounded, in one of four words, and a flag that was not checked says so on its face.
| Grounding | Means |
|---|---|
ran |
executed a command or query and read the output |
read |
opened the source and read the relevant lines |
fetched |
retrieved the cited external work and checked it says what the document claims |
assumed |
not checked — recorded as unverified, never asserted either way |
assumed is not failure. It is the honest label for a flag you could not close, and a reviewer who never writes it is hiding something. What is forbidden is asserting at read confidence something you only assumed.
Run the pass
Work the seven targets. Each exists because this class of defect fails silently — the document reads fine and the claim is wrong.
What ships with it
5 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.
- 1mo ago Changed · +1 lines · +216 tokens per session 4218689fd606
- 1mo ago First seen · 105 lines · 0 tokens per session scan A 9bb3bf4e547c
epistemic-editing is a skill published in the GitHub repository EmpiricaAI/empirica (251 stars, last pushed yesterday), licensed MIT. It adds 216 tokens to every session and 2,159 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
workflow-builder
Design, build, and maintain autonomous OpenClaw workflows (stewards). Use when creating new workflow agents, improving existing ones, evaluating automation opportunities, or debugging workflow reliability. Triggers on "build a workflow", "create a steward", "automate this process", "workflow audit", "what should I…
smart-delegation
Intelligent task delegation — route to think with deep reasoning for hard problems, or Grok for unfiltered takes. Teaches when to escalate, how to pack context into sub-agent spawns, and how to communicate delays transparently. Default: handle directly on chat (thinking off). Escalate only when the quality gain…
claude-code
Route real repo work to Claude Code instead of editing by hand. Triggers on "claude code" or "cc", and on any request to edit, fix, refactor, or open a PR in a repo outside /.openclaw/workspace. Claude Code picks up the repo's CLAUDE.md / AGENTS.md, applies its standards, and knows the /ai-coding-config:multi-review…
review
A pause before an artifact goes into the world. Reviews external comms, money, calendar, public posts, or send-as-operator actions through a small panel of independent lenses (empathy first) and returns a verdict of pass / edit / hold / block.
cortex
Personal knowledge compiler and memory system. Ingests raw sources (documents, notes, transcripts, captures) into a structured, interlinked knowledge base. Maintains living entity pages, learning analysis, and the MEMORY.md routing table. Replaces the librarian skill.
drive-to-done
Drive a task all the way to a verified done state — write DoD first, verify each item with evidence, stop only at named stop conditions.