audit-agents

audit-agents is a command for coding agents from datacore-one/datacore. It costs 8 tokens per session (1,222 once invoked), scanned A, original, MIT.

Command "audit-agents" from datacore-one/datacore, covering /audit-agents, command context, when to reference dip-0016, quick reference and agents this command invokes.

Command

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 commands/datacore-one/datacore/audit-agents
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore

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 audit-agents

README.md
[![agentmods](https://agentmods.dev/badge/commands/datacore-one/datacore/audit-agents.svg)](https://agentmods.dev/commands/datacore-one/datacore/audit-agents)
Your own site
<a href="https://agentmods.dev/commands/datacore-one/datacore/audit-agents"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/audit-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,222 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00008 $0.01222
Opus 5 $0.00004 $0.00611
Sonnet 5 $0.00002 $0.00244
Haiku 4.5 $0.00001 $0.00122

Measured today against content hash 2a5405a779bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-agents 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 today.

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.

.datacore/commands/audit-agents.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit-agents

Command Context

When to Reference DIP-0016

Always reference when:

  • Auditing agent registry entries
  • Checking spawn relationships
  • Validating reads/writes paths
  • Injecting Agent Context sections

Key decisions this DIP informs:

  • Registry entry requirements
  • Agent Context section format
  • Spawn cycle detection
  • Compliance scoring

Quick Reference

Question Answer
Registry file? .datacore/registry/agents.yaml
Commands registry? .datacore/registry/commands.yaml
Agent files? .datacore/agents/*.md
What DIPs govern this? DIP-0016 (Agent Registry)

Agents This Command Invokes

Agent Purpose
agent-registry-auditor Compliance audit

Integration Points

  • DIP-0016 - Agent registry specification
  • /diagnostic - System health complement

Audit agents for DIP-0016 compliance and registry alignment.

Workflow

Step 1: Understand Intent

If user invoked /audit-agents with no arguments, ask:

"What would you like to audit?"

  1. Full audit - Scan all agents, check registry, detect issues (Recommended)
  2. Specific agent - Audit a single agent by name
  3. Generate missing - Only generate entries for unregistered agents
  4. Fix issues - Run audit and auto-fix with confirmation

If intent is clear from context (e.g., /audit-agents ai-task-executor), proceed directly.

Step 2: Run Audit

Invoke the agent-registry-auditor agent with the selected scope:

Launching agent-registry-auditor...

The auditor will:

  1. Scan all agent files in .datacore/agents/ and module agent directories
  2. Compare against .datacore/registry/agents.yaml
  3. Validate spawn relationships and detect cycles
  4. Check that read paths exist
  5. Generate compliance report

Step 3: Present Results

Show the compliance report:

AGENT REGISTRY AUDIT REPORT
═══════════════════════════════════════════════════════════════

Summary:
  Total agents:        25
  Fully compliant:     22
  Needs attention:      3

Issues:
  [!] agent-name - Missing registry entry
  [!] other-agent - Spawns non-existent target
  ...

═══════════════════════════════════════════════════════════════

Read the full file on GitHub · 212 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. today First seen · 212 lines · 8 tokens per session scan A 2a5405a779bc

Subscribe to this mod's changes

audit-agents is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 1,222 once invoked, about $0.0000 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.