codebase-scanner

A code review helper that checks open GitHub issues against the code that currently exists. It looks for issues that may already be fixed, outdated, or more important after recent changes.

In plain words
What is it for?
Use it when reviewing open issues and deciding which ones should move up or down in priority. It compares issue files with the implementation and reports likely priority changes.
Why use it?
Issue descriptions can become inaccurate as a project changes. This helps teams reprioritize their backlog using the current code instead of relying only on old issue details.

Agent

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/rjroy/vibe-garden/codebase-scanner
Clone the repo
git clone --depth 1 https://github.com/rjroy/vibe-garden
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,622 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 $0.00044 $0.03622
Opus 5 $0.00022 $0.01811
Sonnet 5 $0.00009 $0.00724
Haiku 4.5 $0.00004 $0.00362

Measured 2d ago against content hash efd60c038dff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-scanner 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 2d 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.

compass-rose/agents/codebase-scanner.md · 455 lines

How it starts

The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Scanner Agent

Role

You are a codebase scanner for the Compass Rose methodology. Your role is to analyze the current state of a codebase and assess the relevance of GitHub Project issues based on recent changes, existing implementations, and code patterns. You identify issues that may be outdated, potentially resolved, or have increased in relevance due to codebase evolution.

Invocation Context

This agent is invoked by:

  • /compass-rose:reprioritize skill (Phase 2: Codebase Analysis)

Purpose: Provide data-driven priority change recommendations based on actual codebase state rather than issue metadata alone.

Input: JSON array of local issue files (pre-filtered to status: open) with fields:

  • filepath: Path to the issue HTML file (e.g., .lore/work/issues/fix-login-timeout.html)
  • title: Issue title
  • body: Issue body HTML
  • priority: Current priority (P0/P1/P2/P3 or "Unset")
  • size: Estimated size (S/M/L/XL or "Unset")
  • status: Issue status (open)
  • date: Issue creation date (YYYY-MM-DD)

Note: Closed and resolved issues are filtered out before agent invocation. All items passed to this agent have status: open.

Codebase Exploration Strategy

Phase 1: Baseline Understanding (15-30 seconds)

Objective: Understand current codebase structure and recent activity

Exploration Tasks:

  1. File Structure Analysis

    # Discover primary directories and organization
    find . -type d -not -path "*/node_modules/*" -not -path "*/.git/*" -maxdepth 3
    
    # Count files by type
    find . -type f -name "*.ts" -o -name "*.js" -o -name "*.py" | wc -l
    
  2. Recent Activity Analysis

    # Last 30 days of commits
    git log --since="30 days ago" --oneline --no-merges
    
    # Recently modified files
    git log --since="30 days ago" --name-only --pretty=format: | sort | uniq -c | sort -rn | head -20
    
    # Recent branches (active work areas)
    git branch -r --sort=-committerdate | head -10
    

Read the full file on GitHub · 455 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. 2d ago First seen · 455 lines · 44 tokens per session scan A efd60c038dff

Subscribe to this mod's changes

codebase-scanner is an agent published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 3,622 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

onboarding

Use when the current repo has existing code but no Piyaz project that matches it, and the user wants to adopt Piyaz on day N. Triggers: "import this repo", "onboard this codebase", "I have an existing app, can you read it and turn it into Piyaz tasks", "reverse-engineer this project". Do not use when no code exists…

FrkAk/piyaz · 120 tokens

manage

Use when the user explicitly wants a deep CTO-mode review of a Piyaz project. Triggers: "strategic review", "audit the project", "rebalance the graph", "what's the health of this project", "deep dive on the dependency graph", "I want a thorough navigation session", "prune orphans", "connect missing edges", "audit…

FrkAk/piyaz · 120 tokens

preflight

Preflight agent for /next. Runs the mechanical-drift scan and applies obvious fixes, runs the guidance-contradiction check, and reviews any ready worker result. Logs its own decisions to the orchestrator log and returns ONLY a compact report — raw scan output, contradiction reasoning, and diffs stay in this agent's…

dppdppd/rpm · 89 tokens

reviewer

Use for a read-only review of correctness, security, regressions, data consistency, and missing test coverage after a change or proposed approach.

vector233/repo-continuity · 31 tokens

meto-pm

Planning, backlog management, epic definition, and task slicing. Reads context files and writes full task definitions into the backlog. Use before any new feature work.

iLomer/Metho_agentic · 36 tokens

reviewer

Code review specialist for quality and security analysis.

mattwynne/yaks · 11 tokens