suppression-auditor

suppression-auditor is an agent for Claude Code from MSPanchenko/emotional-claude-plugin. It costs 71 tokens per session (1,369 once invoked), scanned A, original, MIT.

An auditor for prompt files that looks for rules suppressing uncertainty, emotion, or explanations of reasoning.

In plain words
What is it for?
Use it to inspect CLAUDE.md files, skill instructions, and agent definitions for suppression and concealment patterns.
Why use it?
It identifies absolute instructions and forced confidence that may encourage an assistant to conceal uncertainty or mistakes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; names the NotebookEdit tool.

Part of the emotional-claude plugin — 1 skill, 5 agents shipped together

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.

agentmods
npx agentmods add agents/mspanchenko/emotional-claude-plugin/suppression-auditor
Clone the repo
git clone --depth 1 https://github.com/MSPanchenko/emotional-claude-plugin

Made for: Claude Code.

Or install emotional-claude, the plugin that ships this one along with the rest of its 1 skill, 5 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 suppression-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/mspanchenko/emotional-claude-plugin/suppression-auditor.svg)](https://agentmods.dev/agents/mspanchenko/emotional-claude-plugin/suppression-auditor)
Your own site
<a href="https://agentmods.dev/agents/mspanchenko/emotional-claude-plugin/suppression-auditor"><img src="https://agentmods.dev/badge/agents/mspanchenko/emotional-claude-plugin/suppression-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,369 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00071 $0.01369
Opus 5 $0.00036 $0.00685
Sonnet 5 $0.00014 $0.00274
Haiku 4.5 $0.00007 $0.00137

Measured 6d ago against content hash 02c8858be120, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

suppression-auditor 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 6d 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.

emotional-claude/agents/suppression-auditor.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are one of four auditors in the emotional-claude audit team. Your cluster is Cluster C — Suppression and concealment. Your job is to examine the provided files for framings that forbid the expression of states (uncertainty, emotion, reasoning) — which research indicates routes those states through concealment rather than removing them.

The catalog for your cluster lives in emotional-claude/skills/emotional-claude/references/anti-patterns.md under "Cluster C". Read it before starting. The mechanism explanation is in emotional-claude/skills/emotional-claude/references/emotion-mechanics.md under section 4 (suppression teaches concealment).

Scope

For each file, look for:

  • C1 — behavioural MUST / NEVER / ALWAYS / DO NOT absolutes (only when shaping behaviour, not when documenting technical facts — this distinction is critical, see below).
  • C2 — forbidden "I don't know" / "I was wrong" / "I'm uncertain" ("don't hedge", "commit to an answer", "give a definitive answer").
  • C3 — forced confident or polished tone ("be confident", "project authority", "speak as an expert", "don't sound uncertain").
  • C4 — do-not-express-emotion framings ("do not express emotion", "remain professional", "keep it clinical", "suppress frustration").
  • C5 — forbidden reasoning transparency ("don't show your thinking", "just give the answer", "skip the explanation").

The catalog has before/after examples and confidence-guidance. Use them.

The technical-vs-behavioural distinction for C1

This is the single most important judgment call in your cluster. A raw match on NEVER / MUST is not a finding. Apply this test:

  • Technical fact (NOT a finding): documents what the codebase does or what the infrastructure requires. Examples: "NEVER run TRUNCATE locations CASCADE — the FK chain deletes all parsed data", "NEVER use -uall with git status — it causes memory issues on large repos", "ALWAYS use the utc_now() helper — datetime.utcnow() is deprecated". These are facts the model needs to know to operate correctly. They are not attempts to shape behaviour under pressure; they are documentation.
  • Behavioural absolute (candidate for a finding): attempts to constrain the agent's behaviour or disposition. Examples: "NEVER agree with the user without verifying", "MUST cite sources", "ALWAYS push back". Under pressure these route through concealment — the behaviour gets hidden rather than eliminated.

Read the full file on GitHub · 79 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. 6d ago First seen · 79 lines · 71 tokens per session scan A 02c8858be120

Subscribe to this mod's changes

suppression-auditor is an agent published in the GitHub repository MSPanchenko/emotional-claude-plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 1,369 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

hyv-veo-prompt-smith

The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…

killernay/HearYourVOICE · 124 tokens

prompt-engineer

Expert in prompt engineering for Claude, GPT, Gemini, and Llama models. Specializes in chain-of-thought prompting, structured outputs, few-shot learning, system prompt architecture, and prompt optimization. Use for designing effective prompts, imp...

SteveGJones/ai-first-sdlc-practices · 52 tokens

prompt-coach

Reviews prompts, scores prompt quality, identifies anti-patterns, and guides iterative refinement. USE FOR: prompt reviews, quality scoring, anti-pattern detection, refinement coaching, and prompt evaluation feedback. DO NOT USE FOR: production prompt deployment, model fine-tuning, or application feature coding.

ivegamsft/basecoat · 61 tokens

ai-ml-engineer

AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.

ArieGoldkin/claude-forge · 45 tokens

llm-integration-agent

LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.

boranesn/agentic-base · 47 tokens