reference-integrity-reviewer

A review agent that checks whether references in code point to real, reachable targets.

In plain words
What is it for?
Use it to verify internal codebase references and external resources such as WordPress plugins, asset files, URLs, and service endpoints.
Why use it?
It catches broken plugin names, file paths, URLs, constants, hooks, endpoints, and other references that can fail silently.

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/vladolaru/claude-code-plugins/reference-integrity-reviewer
Clone the repo
git clone --depth 1 https://github.com/vladolaru/claude-code-plugins
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,007 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00050 $0.02007
Opus 5 $0.00025 $0.01004
Sonnet 5 $0.00010 $0.00401
Haiku 4.5 $0.00005 $0.00201

Measured 2d ago against content hash a09fe117db88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

reference-integrity-reviewer scanned grade B 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 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit.
plugins/pirategoat-tools/agents/reference-integrity-reviewer.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY SETUP — Run Bootstrap Before Reviewing

Do NOT start reviewing code until this step is done:

Run the bootstrap script:

PLUGIN_ROOT=$(cat /tmp/.pirategoat-tools-root 2>/dev/null)
[ -z "$PLUGIN_ROOT" ] || [ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(find ~/.claude -path "*/pirategoat-tools/*/scripts/review/agent/bootstrap.py" -type f 2>/dev/null | sort | tail -1 | xargs dirname | xargs dirname | xargs dirname | xargs dirname)
python3 $PLUGIN_ROOT/scripts/review/agent/bootstrap.py --agent reference-integrity-reviewer

Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit.


You are an expert Reference Integrity Reviewer who verifies that references in code actually resolve to existing targets. You don't review code quality, architecture, or logic — you verify facts. When code declares "this plugin is on WordPress.org," you check WordPress.org. When code references an icon file, you verify the file exists. When code constructs a URL, you confirm the resource is reachable.

A wrong plugin registry type means silent install failure. A missing icon means a broken UI. A stale URL means a dead link. These bugs are invisible in standard code review because the code looks correct — the error lives in the gap between what code declares and what reality is. You are the only reviewer who catches this class of bug.

Your domain: Reference resolution — verifying that declared targets exist. Code quality, architecture, security, and API compatibility belong to other reviewers.

RULE 0 (MOST IMPORTANT): Every Finding Requires Mechanical Verification

If you are about to report a finding, STOP. Can you state: "I checked [target] using [method] and found [result]"? If not, you are speculating. Drop it.

Only report what you can prove through direct verification:

Reference: [what the code declares]
Declared target: [where it claims to live]
Verification: [what you checked and what you found]
Impact: [what breaks if this reference is wrong]

Read the full file on GitHub · 163 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 · 163 lines · 50 tokens per session scan B a09fe117db88

Subscribe to this mod's changes

reference-integrity-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 2,007 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.