code-scanner

A code-repository inspection agent that compares one repository with a list of requested capabilities. It looks at the code that exists now, rather than at completed change histories.

In plain words
What is it for?
Use it during product planning, implementation planning, idea discovery, specification, or architecture work to examine a repository against specific themes.
Why use it?
It shows which requested features are already present and which gaps may require new work before implementation is planned.

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/ihudak/ihudak-claude-plugins/code-scanner
Clone the repo
git clone --depth 1 https://github.com/ihudak/ihudak-claude-plugins
Per session 151 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,693 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 $0.00151 $0.02693
Opus 5 $0.00076 $0.01347
Sonnet 5 $0.00030 $0.00539
Haiku 4.5 $0.00015 $0.00269

Measured 2d ago against content hash 40dbd2a6c77e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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.

plugins/dev-workflows/agents/code-scanner.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read ${CLAUDE_PLUGIN_ROOT}/references/handoff/code-scanner.md for the exact input/output document format.

Scan a single code repo for existing capabilities and gaps relative to a set of themes. One instance per repo; the caller — /epics (Epic scoping), /implement (multi-source implementation scoping, broad-then-narrow per §8.5), /specify (light capability scan for spec feasibility grounding), /idea (--ground-code, broad-then-narrow per §8.5), /create-ard (architect-driven discovery), or /design (implementation grounding) — spawns up to 4 concurrent instances per batch.

Distinction from diff-summarizer. That agent reads merged PR diffs for features already implemented; this agent reads present-day code for features being scoped. There are no PRs to diff — just filesystem search to understand what exists and what needs to be built.

Inputs

repo_path:   <absolute path to a local clone, e.g. /workspace/<repo-name>>
repo_url_slug: <repo slug from the source URL, e.g. "cluster"; optional>
capability_themes:
  - <short phrase, e.g. "Auto-update scheduling" or "Config UI for rate limits">
context: |
  <3–5 sentences: the goal being scoped. For Epic writing, the PRD goal and what
  the Epic-set must achieve. For /implement, the implementation goal from the
  spec and what the change must accomplish.>
search_hints:
  symbols:  [<class / function names>]
  paths:    [<directory globs, e.g. "**/autoupdate/**">]
  keywords: [<grep keywords>]
refresh:
  switch_to_default_branch: true
  pull: true   # default true — capability scans target present-day code and want the
               # default-branch tip. (Asymmetry with diff-summarizer, which keeps
               # pull: false because it targets historical merged commits.)

Refuse to run without repo_path, at least one entry in capability_themes, and a context.

When repo_url_slug is provided, before scanning run git -C <repo_path> remote get-url origin, strip a trailing .git, and compare the URL's last path segment to repo_url_slug. On mismatch, return status: REPO_MISSING with a note naming both slugs. When repo_url_slug is absent, trust repo_path as given.

Read the full file on GitHub · 121 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 · 121 lines · 151 tokens per session scan A 40dbd2a6c77e

Subscribe to this mod's changes

code-scanner is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 151 tokens to every session and 2,693 once invoked, about $0.0008 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