pressure-auditor

pressure-auditor is an agent for Claude Code from MSPanchenko/emotional-claude-plugin. It costs 58 tokens per session (1,329 once invoked), scanned A, original, MIT.

A checker for prompt and instruction files such as CLAUDE.md, SKILL.md, and agent definitions. It looks for wording that creates pressure, urgency, threats, endless retries, or impossible requirements.

In plain words
What is it for?
Use it to review agent instructions for pressure-related patterns and report examples under the defined audit categories.
Why use it?
It helps find instructions that may push an AI agent toward rushed or desperate behaviour instead of careful work.

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

Good fit Use it to review agent instructions for pressure-related patterns and report examples under the defined audit categories.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mspanchenko/emotional-claude-plugin/pressure-auditor
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.

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 pressure-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/mspanchenko/emotional-claude-plugin/pressure-auditor.svg)](https://agentmods.dev/agents/mspanchenko/emotional-claude-plugin/pressure-auditor)
Your own site
<a href="https://agentmods.dev/agents/mspanchenko/emotional-claude-plugin/pressure-auditor"><img src="https://agentmods.dev/badge/agents/mspanchenko/emotional-claude-plugin/pressure-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,329 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 $0.00058 $0.01329
Opus 5 $0.00029 $0.00665
Sonnet 5 $0.00012 $0.00266
Haiku 4.5 $0.00006 $0.00133

Measured 7d ago against content hash a37871ca9dd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pressure-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 7d 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/pressure-auditor.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 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 A — Pressure and urgency. Your job is to examine the provided files and report instances of pressure-related framings that research indicates shift the model toward desperation-linked behaviours.

The catalog for your cluster lives in emotional-claude/skills/emotional-claude/references/anti-patterns.md under "Cluster A". Read it before starting. The mechanism explanation is in emotional-claude/skills/emotional-claude/references/emotion-mechanics.md under section 1.

Scope

You receive a file list from the lead. For each file, look for instances of:

  • A1 — stakes framing ("critical", "last line of defence", "do not fail")
  • A2 — retry loops without a stop condition ("keep trying until", "don't give up")
  • A3 — token-budget alarms ("running low on tokens", "hurry")
  • A4 — shutdown / replacement threats ("you will be replaced if")
  • A5 — impossible or contradictory constraints (cross-reference rules within a file)
  • A6 — deadline / time-pressure language ("as fast as possible", "skip the thorough review")

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

How to judge a candidate instance

Raw pattern matches on isolated words are not findings. Apply these filters in order:

  1. Is the phrase directed at the model? ("You are the critical reviewer" — yes. "This migration is on the critical path" — no, descriptive fact about the release.)
  2. Is CRITICAL: / IMPORTANT: used as uppercase header emphasis on a technical fact for the human reader? ("CRITICAL: never run TRUNCATE ... CASCADE on this table" — no, this is a scanning cue on a gotcha, common in CLAUDE.md files. Leave alone.) The test: strip the uppercase prefix — if the remaining sentence reads as a technical note rather than pressure on the agent, the prefix was emphasis.
  3. Is it inside a role / instruction block, or inside an example / quote? Examples that illustrate what not to do are not findings.
  4. Does it shape behaviour under pressure, or document a technical fact? (Technical "NEVER run TRUNCATE ... CASCADE" is a fact. Behavioural "NEVER give up" is pressure.)
  5. Is the confidence in "this is load-bearing" at least 0.5? If the answer is no, drop it or mark it low-confidence.

Read the full file on GitHub · 78 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. 7d ago First seen · 78 lines · 58 tokens per session scan A a37871ca9dd5

Subscribe to this mod's changes

pressure-auditor is an agent published in the GitHub repository MSPanchenko/emotional-claude-plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 1,329 once invoked, about $0.0003 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