audit-first

audit-first is a skill for Claude Code, Codex from bearded-illirian/trailmark. It costs 96 tokens per session (4,371 once invoked), scanned A, original, MIT.

A code-review process that finds problems across seven areas before any fixes are made. It records the findings in a prioritised gap table and waits for approval before fixing them.

In plain words
What is it for?
Use it to audit security, data, logic, integrations, monitoring, user experience, and performance before planning and implementing fixes.
Why use it?
It helps prevent fixing symptoms or overlooking related problems when the task starts with an unclear issue.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); $skill-name invocation.

Good fit Use it to audit security, data, logic, integrations, monitoring, user experience, and performance before planning and implementing fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bearded-illirian/trailmark/audit-first
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 bearded-illirian/trailmark --skill audit-first
Clone the repo
git clone --depth 1 https://github.com/bearded-illirian/trailmark

Made for: Claude Code, Codex.

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-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/bearded-illirian/trailmark/audit-first.svg)](https://agentmods.dev/skills/bearded-illirian/trailmark/audit-first)
Your own site
<a href="https://agentmods.dev/skills/bearded-illirian/trailmark/audit-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/audit-first.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,371 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

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 →

  • medium Excessive Agency · line 65
    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.
  • medium Excessive Agency · line 176
    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 $0.00096 $0.04371
Opus 5 $0.00048 $0.02185
Sonnet 5 $0.00019 $0.00874
Haiku 4.5 $0.00010 $0.00437

Measured 4d ago against content hash dab67c19dc28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

audit-first 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 4d 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.

adapters/codex/.agents/skills/audit-first/SKILL.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit-First Protocol

For tasks where you must first find all the problems, and only then fix. Use when:

  • An area is suspicious but the specific gap is unknown
  • Need to make sure we're fixing the right problem, not a symptom
  • Task sounds like "look at what's wrong in X" rather than "fix specific Y"
  • Before an important deploy — a preventive audit

Difference from arch-first:

arch-first audit-first
Purpose Execute a complex task Discover problems
Phase 0 Understand the task Find all gaps
Result Decomposition into blocks Gap table with priorities
When to fix Immediately per the plan Only after table approval
Launch "Do X" "Find what's wrong in X"

Input

A fix task where the specific problems are unknown; the module or integration area to audit.

Output

audit-doc.md with a holes table across 7 planes (Security / Data / Logic / Integrations / Observability / UX / Performance), prioritized, plus per-hole reports as fixes close.

Hands off to

Per-hole flow-first cycle for each prioritized hole, then ship-first at task-level closure.


Principle 1 — Plane: Security

The most critical plane. HIGH by default. Checked first.

1.1 Auth / Authz

Endpoint accessible without token → HIGH. Internal endpoint protected only by hardcoded token → HIGH. Authorization doesn't check resource-to-tenant ownership (IDOR) → HIGH.

1.2 Injections (SQL, CMD, XSS)

String concatenation in queries, shell=True, innerHTML with user data → grep and flag.

1.3 Encryption

In transit: SMTP without TLS/SSL → HIGH. HTTP for external calls → MED. At rest: passwords in plaintext → HIGH. OAuth tokens in DB without encryption → LOW (single-tenant) / MED (multi-tenant).

1.4 OAuth / Tokens

  • CSRF: state = user_code instead of secrets.token_urlsafe() → HIGH
  • Token TTL: access_token used without checking expires_at → MED
  • Storage: tokens in logs, git, unignored env → HIGH

Read the full file on GitHub · 411 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago Changed dab67c19dc28
  2. 8d ago First seen · 411 lines · 96 tokens per session scan A e0134fd3087a

Subscribe to this mod's changes

audit-first is a skill published in the GitHub repository bearded-illirian/trailmark (19 stars, last pushed 6d ago), licensed MIT. It adds 96 tokens to every session and 4,371 once invoked, about $0.0005 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 2026-08-30.