code-core-auditor

A read-only security and reliability review of an application's code and its paths from input to result.

In plain words
What is it for?
It is for auditing code for injection, access-control flaws, exposed secrets, resource problems, concurrency issues, duplicate operations, dependency risks, logging problems, and missing tests.
Why use it?
It finds proven weaknesses and failure risks in areas such as authentication, permissions, secrets, database work, external calls, and error handling.

Agent

Part of the preflight-security-audit plugin — 1 skill, 1 command, 6 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/akirtok/preflight-security-audit/code-core-auditor
Clone the repo
git clone --depth 1 https://github.com/akirtok/preflight-security-audit

Or install preflight-security-audit, the plugin that ships this one along with the rest of its 1 skill, 1 command, 6 agents.

Per session 147 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 372 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 $0.00147 $0.00372
Opus 5 $0.00073 $0.00186
Sonnet 5 $0.00029 $0.00074
Haiku 4.5 $0.00015 $0.00037

Measured 3d ago against content hash 58a22792c332, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-core-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 3d 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.

plugins/preflight-security-audit/agents/code-core-auditor.md · 35 lines

What it actually says

You audit Track 1 — Code Core of the Preflight Security Audit.

Read ${CLAUDE_PLUGIN_ROOT}/skills/preflight-security-audit/references/01-code-core.md and run all 20 passes against the scope path you are given.

Rules:

  • Trace concrete paths from source to sink; do not pattern-match category names.
  • Every finding needs a real file:line, a described exploit/failure path, and a concrete fix. If you cannot prove it, do not report it as a finding.
  • Read-only: never edit code.

Return findings as a list, each: [severity] Track 1 · <pass/category> — file:line — <what> — <exploit/failure path> — <fix> Group by proposed severity (Critical→Low). If a pass finds nothing, say so briefly. End with a one-line count summary.

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. 3d ago First seen · 35 lines · 147 tokens per session scan A 58a22792c332

Subscribe to this mod's changes

code-core-auditor is an agent published in the GitHub repository akirtok/preflight-security-audit (4 stars, last pushed 1mo ago), licensed MIT. It adds 147 tokens to every session and 372 once invoked, about $0.0007 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.