conduct-gxp-audit

conduct-gxp-audit is a skill for Claude Code from pjt222/agent-almanac. It costs 89 tokens per session (2,581 once invoked), scanned A, original, MIT.

A step-by-step guide for auditing computer systems and processes used in regulated fields such as drug manufacturing, clinical research, and laboratory work. It covers planning, evidence gathering, classifying findings, corrective actions, reporting, and follow-up.

In plain words
What is it for?
Use it for internal audits, software supplier checks, inspection-readiness reviews, and investigations into deviations or data-integrity concerns.
Why use it?
It gives audits a consistent structure and helps teams document compliance problems and the actions needed to address them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the agent-almanac plugin — 122 skills, 76 agents shipped together

Good fit Use it for internal audits, software supplier checks, inspection-readiness reviews, and investigations into deviations or data-integrity concerns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pjt222/agent-almanac/conduct-gxp-audit
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 pjt222/agent-almanac --skill conduct-gxp-audit
Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac

Made for: Claude Code.

Or install agent-almanac, the plugin that ships this one along with the rest of its 122 skills, 76 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 conduct-gxp-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/pjt222/agent-almanac/conduct-gxp-audit/github.svg)](https://agentmods.dev/skills/pjt222/agent-almanac/conduct-gxp-audit)
Your own site
<a href="https://agentmods.dev/skills/pjt222/agent-almanac/conduct-gxp-audit"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/conduct-gxp-audit/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 conduct-gxp-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/pjt222/agent-almanac/conduct-gxp-audit"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/conduct-gxp-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,581 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 pass 7 Sept 2026
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 $0.00089 $0.02581
Opus 5 $0.00044 $0.01290
Sonnet 5 $0.00018 $0.00516
Haiku 4.5 $0.00009 $0.00258

Measured 7d ago against content hash 7fda5dfcb329, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

conduct-gxp-audit 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.

i18n/caveman-lite/skills/conduct-gxp-audit/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conduct GxP Audit

Plan and execute a GxP audit of computerized systems, data integrity practices, or regulated processes.

When to Use

  • Scheduled internal audit of a validated computerized system
  • Supplier/vendor qualification audit for GxP-relevant software
  • Pre-inspection readiness assessment before a regulatory audit
  • For-cause audit triggered by a deviation, complaint, or data integrity concern
  • Periodic review of a validated system's compliance posture

Inputs

  • Required: Audit scope (system, process, or site to audit)
  • Required: Applicable regulations (21 CFR Part 11, EU Annex 11, GMP, GLP, GCP)
  • Required: Previous audit reports and open CAPA items
  • Optional: System validation documentation (URS, VP, IQ/OQ/PQ, traceability matrix)
  • Optional: SOPs, training records, change control logs
  • Optional: Specific risk areas or concerns triggering the audit

Procedure

Step 1: Develop the Audit Plan

# Audit Plan
## Document ID: AP-[SYS]-[YYYY]-[NNN]

### 1. Objective
[State the purpose: scheduled, for-cause, supplier qualification, pre-inspection]

### 2. Scope
- **System/Process**: [Name and version]
- **Regulations**: [21 CFR Part 11, EU Annex 11, ICH Q7, etc.]
- **Period**: [Date range of records under review]
- **Exclusions**: [Any areas explicitly out of scope]

### 3. Audit Criteria
| Area | Regulatory Reference | Key Requirements |
|------|---------------------|------------------|
| Electronic records | 21 CFR 11.10 | Controls for closed systems |
| Audit trail | 21 CFR 11.10(e) | Secure, computer-generated, time-stamped |
| Electronic signatures | 21 CFR 11.50 | Manifestation, legally binding |
| Access controls | EU Annex 11, §12 | Role-based, documented |
| Data integrity | MHRA guidance | ALCOA+ principles |
| Change control | ICH Q10 | Documented, assessed, approved |

### 4. Schedule
| Date | Time | Activity | Participants |
|------|------|----------|-------------|
| Day 1 AM | 09:00 | Opening meeting | All |
| Day 1 AM | 10:00 | Document review | Auditor + QA |
| Day 1 PM | 13:00 | System walkthrough | Auditor + IT + System Owner |
| Day 2 AM | 09:00 | Interviews + evidence collection | Auditor + Users |
| Day 2 PM | 14:00 | Finding consolidation | Auditor |
| Day 2 PM | 16:00 | Closing meeting | All |

### 5. Audit Team
| Role | Name | Responsibility |
|------|------|---------------|
| Lead Auditor | [Name] | Plan, execute, report |
| Subject Matter Expert | [Name] | Technical assessment |
| Auditee Representative | [Name] | Facilitate access and information |

Read the full file on GitHub · 278 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 · 278 lines · 89 tokens per session scan A 7fda5dfcb329

Subscribe to this mod's changes

conduct-gxp-audit is a skill published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 2,581 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 2026-09-03.