pos: Skill for Claude Code

.claude/skills/pos-audit/SKILL.md

pos-audit is a skill for Claude Code from xcota/pos. It costs 16 tokens per session (1,666 once invoked), scanned A, original, MIT.

A health-check tool for a Personal OS workspace, including its context files, knowledge graph, and other system layers. A knowledge graph is a collection of linked notes about people, topics, or projects.

In plain words
What is it for?
Use it to inspect context files, count and assess knowledge notes and links, identify unlinked entries, and score overall system health.
Why use it?
It reveals missing or weak parts of the workspace and shows where the system's information is not properly connected.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

This is xcota/pos's own configuration. It tells Claude Code how to work on pos itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pos configures →

View source ↗ xcota/pos
Reuse

Borrowing it

Nothing to install: this file belongs to xcota/pos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/xcota/pos/main/.claude/skills/pos-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/xcota/pos

Made for: Claude Code.

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 pos-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/xcota/pos/pos-audit.svg)](https://agentmods.dev/skills/xcota/pos/pos-audit)
Your own site
<a href="https://agentmods.dev/skills/xcota/pos/pos-audit"><img src="https://agentmods.dev/badge/skills/xcota/pos/pos-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,666 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 76
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • high Agent Snooping · line 109
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • high Agent Snooping · line 112
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • high Agent Snooping · line 112
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • medium Agent Snooping · line 76
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Excessive Agency · line 179
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00016 $0.01666
Opus 5 $0.00008 $0.00833
Sonnet 5 $0.00003 $0.00333
Haiku 4.5 $0.00002 $0.00167

Measured 7d ago against content hash f883aec87d61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pos-audit scanned grade A with 2 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/settings.json 2>/dev/null | python3 -c "

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Enumerates other installed skillslowAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

find .claude/skills -name "SKILL.md" 2>/dev/null | wc -l

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/skills/pos-audit/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

POS Audit — System Health Check

Scans all Personal OS layers, scores health, surfaces gaps. Invoke: /pos-audit

Step 1: Context Layer

wc -l CLAUDE.md 2>/dev/null
grep "^## " CLAUDE.md 2>/dev/null

Check: exists? >50 lines? Has sections: Identity/Rules, Context, Orchestration, Hard rules, Naming?

Score: 0 (missing) / 1 (exists but thin) / 2 (full, with sections)

Step 2: Knowledge Graph

find knowledge/ -name "*.md" -not -name "AGENTS.md" | wc -l
grep -rl "\[\[" knowledge/ | wc -l

Check: entity count, wikilink coverage (% of files with links), type distribution.

for d in knowledge/*/; do echo "$(basename "$d"): $(find "$d" -name '*.md' -not -name 'AGENTS.md' | wc -l)"; done

Score: 0 (<10 entities) / 1 (10-100) / 2 (100+ with >50% linked AND <5 floating nodes)

Graph health check (mandatory):

# Count floating nodes (0 incoming links)
python3 -c "
import os, re
kg=os.path.join(os.getcwd(), 'knowledge')
incoming={}
entities=set()
for root,dirs,files in os.walk(kg):
    for f in files:
        if f.endswith('.md') and f not in ('AGENTS.md','INDEX.md'):
            name=f.replace('.md','')
            entities.add(name)
            with open(os.path.join(root,f)) as fh:
                for link in re.findall(r'\[\[([^\]]+)\]\]',fh.read()):
                    incoming.setdefault(link,set()).add(name)
floating=[n for n in entities if n not in incoming]
print(f'Floating nodes: {len(floating)}/{len(entities)}')
for n in sorted(floating)[:10]: print(f'  {n}')
"

Also check: wc -c CLAUDE.md — must be < 3500 chars.

Step 3: Projects

ls -d projects/*/AGENTS.md 2>/dev/null | wc -l
ls -d projects/*/context.md 2>/dev/null | wc -l

Score: 0 (no projects) / 1 (some without AGENTS.md) / 2 (all have AGENTS.md + context.md). Fresh vault: if top-level projects/ doesn't exist yet, score N/A — render PROJECTS N/A (fresh vault), keep it out of GAPS, and drop it from the denominator (score /14 not /16). A blank vault is healthy-by-design here.

Read the full file on GitHub · 184 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 · 184 lines · 16 tokens per session scan A f883aec87d61

Subscribe to this mod's changes

pos-audit is a skill published in the GitHub repository xcota/pos (43 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,666 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.