agentmods.dev

epistemic-checkpoint

epistemic-checkpoint is a command for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 39 tokens per session (367 once invoked), scanned A, original, MIT.

A verification command for checking claims about software versions, release status, dates, and whether an API is current.

In plain words
What is it for?
Use it before answering questions about latest versions, preview or stable releases, package versions, API deprecations, and other time-sensitive software facts.
Why use it?
It prevents answers from relying on outdated memory when the facts may have changed since the model was trained.

Command for Claude Code

Written for Claude Code: effort in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the metacognitive-guard plugin — 5 commands, 3 agents shipped together

not rated 6repo 2d ago A scan 39 tokens original MIT

Good fit Use it before answering questions about latest versions, preview or stable releases, package versions, API deprecations, and other time-sensitive software facts.

Compare 6 commands from other repositories ↓
View source ↗ ANcpLua/ancplua-claude-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ANcpLua/ancplua-claude-plugins
Claude Code
/plugin install metacognitive-guard

Made for: Claude Code.

Or install metacognitive-guard, the plugin that ships this one along with the rest of its 5 commands, 3 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-checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/epistemic-checkpoint/github.svg)](https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/epistemic-checkpoint)
Your own site
<a href="https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/epistemic-checkpoint"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/epistemic-checkpoint/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-checkpoint

Your own site · 80×15
<a href="https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/epistemic-checkpoint"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/epistemic-checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 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.
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 $0.00039 $0.00367
Opus 5.5 $0.00016 $0.00147
Sonnet 5.5 $0.00008 $0.00073
Haiku 4.5 $0.00004 $0.00037

Measured 1mo ago against content hash 09bc5543ef9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

epistemic-checkpoint 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.

plugins/metacognitive-guard/commands/epistemic-checkpoint.md · 44 lines

What it actually says

Epistemic Checkpoint

Verify before forming beliefs. Claude's training data is stale — this skill forces verification.

Triggers

Activate when the question involves: software versions, release status (preview/LTS/GA), "current" or "latest" anything, dates after training cutoff, package versions, API deprecations.

Protocol

  1. Recognize uncertainty: "My training data may be stale for: [topic]"
  2. Check local ground truth: Read ${CLAUDE_PLUGIN_ROOT}/blackboard/assertions.yaml
  3. If not found — WebSearch: "[software] [version] release date site:official-docs"
  4. State verified fact: "Based on [source], [software] [version] is [status] as of [date]."
  5. Then proceed with verified baseline.

Output Format

Epistemic Checkpoint

Claim to verify: [what you were about to assume]
Source checked: [assertions.yaml / WebSearch / official docs]
Verified fact: [the actual truth]
Confidence: [high/medium/low]

Proceeding with verified baseline...

Red Flags

If you think... Do this instead
"I'm pretty sure .NET 10 is..." WebSearch to verify
"This is probably still preview" Check assertions.yaml
"I remember from training" Training is stale, verify
"The user said it's preview" User might be wrong too
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. 1mo ago First seen · 44 lines · 39 tokens per session scan A 09bc5543ef9b

Subscribe to this mod's changes

epistemic-checkpoint is a command published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 367 once invoked, about $0.0002 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 2026-10-01.

DebuggingResearchancplua-fleet
Related

epistemic-checkpoint compared with commands from other repositories

epistemic-checkpoint next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
epistemic-checkpointANcpLua/ancplua-claude-pluginsCommand62d agoMITA39Claude Code
qa-changesOpenHands/extensionsCommand181yesterdayMITA63Claude Code
auditar-cascadingluanpdd/kit-mcpCommand52d agoMITA54Claude Code
react-nativegetsentry/toolkitCommand961yesterdaynoneA0Claude Code
http-serviceMadAppGang/magusCommand14yesterdayMITA27Claude Code
doctordoncheli/don-cheli-sddCommand593mo agoApache-2.0A76Claude Code
doctorfatihkan/badiCommand71mo agoMITA0Claude Code