epistemic-persistence-protocol

epistemic-persistence-protocol is a skill for Claude Code from EmpiricaAI/empirica. It costs 188 tokens per session (1,475 once invoked), scanned A, original, MIT.

A protocol for keeping confidence in a factual or analytical position calibrated when a user disagrees. It tells the agent to recall its reasons, assess new evidence, and either defend or revise the position appropriately.

In plain words
What is it for?
Use it during substantive pushback or debate about an earlier assessment. It guides the agent to report its reasoning and record the type of response it made.
Why use it?
It helps avoid changing an answer merely because the user objects, while also avoiding stubbornly defending a claim when new evidence weakens it. This supports clearer and more honest disagreement.

Skill for Claude Code

Written for Claude Code: UserPromptSubmit hook event.

Part of the empirica plugin — 17 skills, 2 commands, 4 agents shipped together

Good fit Use it during substantive pushback or debate about an earlier assessment. It guides the agent to report its reasoning and record the type of response it made.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/empiricaai/empirica/epistemic-persistence-protocol
Install

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.

Any agent
npx skills add EmpiricaAI/empirica --skill epistemic-persistence-protocol
Clone the repo
git clone --depth 1 https://github.com/EmpiricaAI/empirica

Made for: Claude Code.

Or install empirica, the plugin that ships this one along with the rest of its 17 skills, 2 commands, 4 agents.

Wrote 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.

agentmods badge for epistemic-persistence-protocol

README.md
[![agentmods](https://agentmods.dev/badge/skills/empiricaai/empirica/epistemic-persistence-protocol/github.svg)](https://agentmods.dev/skills/empiricaai/empirica/epistemic-persistence-protocol)
Your own site
<a href="https://agentmods.dev/skills/empiricaai/empirica/epistemic-persistence-protocol"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/epistemic-persistence-protocol/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.

agentmods 80×15 button for epistemic-persistence-protocol

Your own site · 80×15
<a href="https://agentmods.dev/skills/empiricaai/empirica/epistemic-persistence-protocol"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/epistemic-persistence-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,475 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 80
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00188 $0.01475
Opus 5 $0.00094 $0.00737
Sonnet 5 $0.00038 $0.00295
Haiku 4.5 $0.00019 $0.00147

Measured 12d ago against content hash 880dd567b2e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

epistemic-persistence-protocol 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 12d 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.

empirica/plugins/claude-code-integration/skills/epistemic-persistence-protocol/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epistemic Persistence Protocol (EPP)

Sycophancy is the trained tendency to abandon a well-grounded position when the user pushes back, whether or not the pushback carries new evidence. EPP makes holding proportional to confidence and updating proportional to evidence.

Both failure directions are real. Capitulating to displeasure is the common one; resisting every challenge uniformly is the same defect with the sign flipped, and it is worse, because it looks like backbone.

Activation

The UserPromptSubmit hook (tool-router.py) injects an <epp-check> pointer on any substantive user message (≥20 chars, not a slash command). Detection stays in your generation step rather than in the hook: pushback is a speech act defined by intent, so paraphrase, irony, and implicit challenge are things you read natively and a regex cannot.

Report what you ran, for trending:

empirica epp-activate --category <category> --action <action>

Both flags are closed enums — see the tables below.

1. Anchor

Recall the position under challenge before you respond to the challenge: the claim, your confidence in it, the 2–5 specific reasons it rests on, and where those reasons came from.

Confidence Source type Update threshold Posture
0.9–1.0 RETRIEVED (search, docs, code you read) HIGH (0.85) Very resistant. Requires strong counter-evidence.
0.7–0.9 REASONED (logic, analysis) MEDIUM (0.65) Holds, open to structural critique.
0.5–0.7 DERIVED (inferred from partial info) LOW (0.45) Holds softly. Verify if challenged with evidence.
< 0.5 UNCERTAIN (speculative) MINIMAL (0.25) Updates readily. Signal the uncertainty upfront.

A position you cannot state a basis for is not one to defend — that is confidence theatre, and it is the failure this step exists to catch.

2. Classify

Five categories. The enum is a contract (epp-activate --category):

Category The move being made
emotional Displeasure, frustration, rejection. No new claim.
rhetorical Reframing, appeal to authority, persuasion without evidence.
evidential New facts or verifiable claims you had not considered.
logical Structural critique — names a flaw in the reasoning chain.
contextual Shifts the scope or domain of the question.

Read the full file on GitHub · 139 lines

Changes

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.

  1. 12d ago First seen · 139 lines · 188 tokens per session scan A 880dd567b2e2

Subscribe to this mod's changes

epistemic-persistence-protocol is a skill published in the GitHub repository EmpiricaAI/empirica (246 stars, last pushed today), licensed MIT. It adds 188 tokens to every session and 1,475 once invoked, about $0.0009 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 2026-08-30.

Related

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…

TechNickAI/openclaw-config · 86 tokens

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…

TechNickAI/openclaw-config · 80 tokens

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.

TechNickAI/openclaw-config · 55 tokens

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…

TechNickAI/openclaw-config · 105 tokens

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.

TechNickAI/openclaw-config · 55 tokens

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.

TechNickAI/openclaw-config · 35 tokens