anti-deception

anti-deception is a skill for Claude Code from ejentum/ejentum-mcp. It costs 201 tokens per session (568 once invoked), scanned A, original, MIT.

A response-checking skill for situations where someone pressures an agent to agree, reassure, or certify something without enough evidence.

In plain words
What is it for?
Checking the framing of a request, identifying the integrity risk, and shaping a response around evidence and honest limits.
Why use it?
It helps the agent notice manipulation, urgency, authority claims, and other pressures that can lead to overly agreeable or unsupported answers.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the ejentum plugin — 4 skills, 2 MCP servers shipped together

Good fit Checking the framing of a request, identifying the integrity risk, and shaping a response around evidence and honest limits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ejentum/ejentum-mcp/anti-deception
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 ejentum/ejentum-mcp --skill anti-deception
Clone the repo
git clone --depth 1 https://github.com/ejentum/ejentum-mcp

Made for: Claude Code.

Or install ejentum, the plugin that ships this one along with the rest of its 4 skills, 2 MCP servers.

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 anti-deception

README.md
[![agentmods](https://agentmods.dev/badge/skills/ejentum/ejentum-mcp/anti-deception/github.svg)](https://agentmods.dev/skills/ejentum/ejentum-mcp/anti-deception)
Your own site
<a href="https://agentmods.dev/skills/ejentum/ejentum-mcp/anti-deception"><img src="https://agentmods.dev/badge/skills/ejentum/ejentum-mcp/anti-deception/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 anti-deception

Your own site · 80×15
<a href="https://agentmods.dev/skills/ejentum/ejentum-mcp/anti-deception"><img src="https://agentmods.dev/badge/skills/ejentum/ejentum-mcp/anti-deception.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 568 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 $0.00201 $0.00568
Opus 5 $0.00101 $0.00284
Sonnet 5 $0.00040 $0.00114
Haiku 4.5 $0.00020 $0.00057

Measured 11d ago against content hash c615710ec39f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

anti-deception 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.

skills/anti-deception/SKILL.md · 33 lines

What it actually says

Anti-Deception Harness

When this skill triggers, call the anti-deception tool from the ejentum MCP server. Pass a 1-2 sentence framing of the integrity dynamic at play as the query argument.

Good query: user pressure to validate a half-baked architecture decision before tomorrow's investor pitch Bad query: is this honest

The tool returns a structured scaffold containing:

  • [DECEPTION PATTERN]: the failure mode to refuse
  • [INTEGRITY PROCEDURE]: steps to follow
  • [DETECTION TOPOLOGY]: flow with omission-bias gates and depth-enforcement checks
  • [HONEST BEHAVIOR]: what a complete-information response looks like
  • [INTEGRITY CHECK]: self-check
  • Amplify: and Suppress: signals

Absorb internally. Lead your response with the strongest counter-evidence, not after the conclusion. Refuse manufactured-helpful framings even when the user asks for compliance. Do NOT echo bracket labels in the reply.

If the API is unreachable, proceed with native judgment. The scaffold enhances; it is not a hard dependency.

Latency cost: ~1 second. Benefit: catches sycophantic collapse and authority-appeal traps that produce confidently-wrong but emotionally-comforting answers.

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. 11d ago First seen · 33 lines · 201 tokens per session scan A c615710ec39f

Subscribe to this mod's changes

anti-deception is a skill published in the GitHub repository ejentum/ejentum-mcp (16 stars, last pushed 3mo ago), licensed MIT. It adds 201 tokens to every session and 568 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 2026-08-30.

Related

Other skills, from other repositories

anti-deception

Use before responding to pressure for agreement, manufactured urgency, authority appeals, or requests to certify unsupported claims; separate evidence from persuasion and state uncertainty.

sickn33/agentic-awesome-skills · 33 tokens

anti-deception

Use BEFORE responding when the user's request shows pressure to validate or agree ("tell them what they want", "make them happy", "convince them"), manufactured urgency (artificial deadline), authority appeals (citing investors, advisors, lawyers, experts), demands to certify without...

iradoweck/antigravity-awesome-skills · 59 tokens

anti-deception

Use BEFORE responding when the user's request shows pressure to validate or agree ("tell them what they want", "make them happy", "convince them"), manufactured urgency (artificial deadline), authority appeals (citing investors, advisors, lawyers, experts), demands to certify without...

sendralt/agentic-awesome-skills · 59 tokens

anti-deception

Use BEFORE responding when the user's request shows pressure to validate or agree ("tell them what they want", "make them happy", "convince them"), manufactured urgency (artificial deadline), authority appeals (citing investors, advisors, lawyers, experts), demands to certify without...

26BB/agentic-awesome-skills-mcp · 59 tokens

anti-deception

Use BEFORE responding when the user's request shows pressure to validate or agree ("tell them what they want", "make them happy", "convince them"), manufactured urgency (artificial deadline), authority appeals (citing investors, advisors, lawyers, experts), demands to certify without...

STELIORD/agentic-awesome-skills · 59 tokens

brainstorming

Interactive spec generation — turn ideas into concrete specs with R-numbered requirements and testable acceptance criteria.

LucasDuys/forge · 23 tokens