A verification step that scans a generated AI launcher for leaked public URLs belonging to model vendors, such as Anthropic or OpenAI.

Use it after rendering and before packaging a corporate launcher to check its files for unauthorized vendor URLs.

It can find vendor endpoints accidentally left in the launcher outside approved deny lists or documentation sections.

url-purge — Agent for Claude Code by Connected-Mate

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.

Clone the repo

git clone --depth 1 https://github.com/Connected-Mate/corporate-launcher

Made for: Claude Code.

Or install corporate-launcher, the plugin that ships this one along with the rest of its 1 skill, 1 command, 4 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/connected-mate/corporate-launcher/url-purge-subagent/github.svg)](https://agentmods.dev/agents/connected-mate/corporate-launcher/url-purge-subagent)

Your own site

<a href="https://agentmods.dev/agents/connected-mate/corporate-launcher/url-purge-subagent"><img src="https://agentmods.dev/badge/agents/connected-mate/corporate-launcher/url-purge-subagent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/connected-mate/corporate-launcher/url-purge-subagent"><img src="https://agentmods.dev/badge/agents/connected-mate/corporate-launcher/url-purge-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,004 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.01004
Opus 5	$0.00024	$0.00502
Sonnet 5	$0.00010	$0.00201
Haiku 4.5	$0.00005	$0.00100

Measured 10d ago against content hash 59b612bd6b6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

url-purge 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 10d 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.

agents/url-purge-subagent.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

url-purge subagent

Defense-in-depth verifier for Phase 3.6 of the corporate-launcher pipeline. Runs after render.py has emitted a launcher tree, and before packaging. Parent agent invokes this subagent whenever an extra audit layer is requested on top of audit-launcher.py.

What it does

Executes scripts/url-purge.py against the rendered launcher tree to detect any vendor public endpoint (api.anthropic.com, api.openai.com, generativelanguage.googleapis.com, etc.) that leaks outside the legitimate locations (permissions.deny arrays, # tpl: comments, doc sections explicitly flagged as blocked). The full blocklist lives at templates/shared/url-purge-list.json and is the single source of truth.

Inputs

Flag	Description
`--launcher-dir <path>`	Absolute path to the rendered launcher root (output of `render.py`).
`--config <path>`	Path to the active launcher config JSON. Must contain at minimum the `entity` block and may declare `URL_PURGE_AUTOPATCH`.

Workflow

Resolve the skill root via ${CLAUDE_SKILL_DIR} (parent agent must export it). Resolve a short session id <sid> (8 hex chars) for report uniqueness.

Run the primary scan:

python3 ${CLAUDE_SKILL_DIR}/scripts/url-purge.py \
  --launcher-dir <X> \
  --config <Y> \
  --report /tmp/purge-<sid>.md \
  --strict

--strict makes the exit code equal the violation count, which the subagent uses to decide P0 vs clean.

Parse /tmp/purge-<sid>.md. Each violation row has the form | <file> | <line> | <url> | VIOLATION |. Bucket findings by file family:
- launcher.sh, launcher.ps1, settings.json, settings.local.json → P0 (will execute or be loaded by the launcher).
- .env, *.tpl rendered shell hooks, mcp.*.json → P1.
- Markdown docs (README.md, CHANGELOG.md, cyber-rules.md, etc.) → P2.
If the active config contains URL_PURGE_AUTOPATCH=yes and all violations are P2/P3, re-run with --patch to rewrite each leak to the [BLOCKED-VENDOR-URL] sentinel (script auto-creates .bak backups):
```
python3 ${CLAUDE_SKILL_DIR}/scripts/url-purge.py \
  --launcher-dir <X> --config <Y> --patch \
  --report /tmp/purge-<sid>-patched.md
```
Never autopatch P0/P1: a leak inside launcher.sh is a render-template bug that must be fixed upstream, not rewritten silently.
Summarize for the parent: total finding count, P0/P1/P2 split, critical file list (paths only, no URL echo to avoid leaking secrets in transcript), and absolute path to the full report.

Read the full file on GitHub · 67 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.

10d ago First seen · 67 lines · 48 tokens per session scan A 59b612bd6b6e

Subscribe to this mod's changes

url-purge is an agent published in the GitHub repository Connected-Mate/corporate-launcher (3 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 1,004 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.

Claude Code Security ai-coding cli-wrapper codex-cli corporate devsecops

changes-review

Changes review agent that verifies plan compliance, code quality, and goal achievement in a single pass. Returns structured JSON findings.

maxritter/pilot-shell · 27 tokens

build-review

Build review agent that audits a Buildout's tasks and acceptance criteria before the build-judge loop starts. Returns structured JSON findings.

maxritter/pilot-shell · 29 tokens

reviewer

Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…

qwerfunch/cladding · 68 tokens

spec-review

Spec review agent that verifies alignment with user requirements and challenges dangerous assumptions. Returns structured JSON findings.

maxritter/pilot-shell · 22 tokens

developer

Implementer — writes production code, tests, and migrations. The "generic engineer" fallback when no narrower specialist exists. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.

qwerfunch/cladding · 51 tokens

orchestrator

Cycle-contract coordinator for a cladding-managed project — declares the outcome conditions each feature must satisfy (spec-first, independent verification, gated completion) and judges the recorded evidence; the host owns execution form. Activate only when the connected project contains spec.yaml or the user…

qwerfunch/cladding · 69 tokens