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.
npx skills add humanerd-drew/opencode-drewgent --skill project-code-auditgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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.
[](https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/project-code-audit)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/project-code-audit"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/project-code-audit.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01689 |
| Opus 5 | $0.00016 | $0.00844 |
| Sonnet 5 | $0.00007 | $0.00338 |
| Haiku 4.5 | $0.00003 | $0.00169 |
Grade A, and why
project-code-audit scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
echo -n "$path => "; curl -sSL -o /dev/null -w "%{http_code}" "http://localhost:8787$path"; echo How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Code Audit — Dead Code Detection & Safe Cleanup
When to Use
- User asks to "clean up", "remove unused files", or "audit the project"
- Before a refactoring push — first understand what's actually alive
- When you encounter files that "look unused" — verify systematically, don't guess
- When the project has no clear file ownership map
- Always check for AGENTS.md first — if one exists, read it before any audit step
Core Principle
Incremental + Verified. Never delete in bulk without testing. Change one thing, verify it works, move to the next. A big-bang cleanup is a big-bang breakage risk.
This user prefers incremental, test-each-step changes. Start with zero-risk deletions, test immediately, only then discuss medium-risk restructuring.
Step 0 — AGENTS.md (Project Navigation Map)
Before any audit, create or read AGENTS.md. This is the single file every AI agent reads first to understand the project.
What AGENTS.md contains
- Directory structure overview (depth 2-3)
- File naming convention (e.g. verb-noun.kebab-case.ts)
- "What to search for" table — maps user intent to file paths
- Current migration status (what's done, what's pending)
When to create one
- Project has no clear structure documentation
- You're about to do a multi-phase restructuring
- You found yourself searching for files by guessing names
- User complained about "not being able to find things"
AGENTS.md template
# Project Agent Map
> Read this first. Defines directory structure, file naming, and navigation.
## Directory structure
src/
├── domain-a/ (what this contains)
├── domain-b/ (what this contains)
├── api/ (thin route layer)
└── utils/ (shared utilities)
## File naming
- `verb-noun.kebab-case.ts` — search by verb first
- Example: `verify-payment.ts`, `get-daewoon.ts`, `oauth-naver.ts`
## Quick lookup
| Search term | File |
|---|---|
| login/oauth | src/user/oauth-*.ts |
| payment verify | src/payment/verify-payment.ts |
## Current status
- ✅ Phase completed
- 🚧 Phase in progress
- ⬜ Phase planned
What ships with it
2 files 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.
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.
- 4d ago First seen · 187 lines · 33 tokens per session scan A 7c97e6b00792
project-code-audit is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,689 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Tech Debt Auditor
Identifies and prioritizes technical debt in a codebase with an effort/impact matrix.
critical-review
Radical-honesty architectural review — questions code, methodology, design, and operational fitness.
code-simplification
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
aposd-audit
Quantitative design audit. Counts pass-throughs, duplication, doc gaps, naming issues, and exceptions across 5 dimensions, scored 0-4.
Refactor Engine
Improves existing codebases by restructuring for clarity, performance, and maintainability without changing external behavior.
pr
Use when reviewing an incoming GitHub pull request — runs the multi-level (L1-L5) audit against the PR's real diff range, posts findings as one batched review (inline, summary, or local-only), offers the standard fix chain on NEEDSFIX, and optionally merges. The maintainer-side counterpart to /hyperflow:issue. Trigger…