A procedure for safely editing a proxy allowlist, which controls which network domains may be accessed. It covers allowed domains, TLS-pinned services, enforcement modes, reloads, and blocked-traffic checks.

Use it to add or remove allowed domains, handle TLS-pinned hosts, temporarily observe traffic, reload the policy, and check the proxy logs afterward.

It reduces the risk of changing network access rules incorrectly or rebuilding more of the system than necessary. It also verifies that intended traffic works and blocked traffic remains blocked.

How thiagolmoraes/leash configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to thiagolmoraes/leash. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/thiagolmoraes/leash/main/.claude/skills/policy/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/thiagolmoraes/leash

Made for: Claude Code.

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/skills/thiagolmoraes/leash/policy.svg)](https://agentmods.dev/skills/thiagolmoraes/leash/policy)

Your own site

<a href="https://agentmods.dev/skills/thiagolmoraes/leash/policy"><img src="https://agentmods.dev/badge/skills/thiagolmoraes/leash/policy.svg" alt="Measured on agentmods" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 334 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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.00334
Opus 5	$0.00028	$0.00167
Sonnet 5	$0.00011	$0.00067
Haiku 4.5	$0.00006	$0.00033

Measured 6d ago against content hash 04901da0ba07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

policy 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 6d 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.

.claude/skills/policy/SKILL.md · 31 lines

What it actually says

Workflow for changing proxy/policy.yaml. The file is volume-mounted — never rebuild images for policy changes.

Read proxy/policy.yaml and make the requested change:
- New allowed domain → add under the allowlist section, with a comment saying why.
- TLS-pinned host breaking MitM → add to ignore_hosts instead.
- Profiling a new CLI's traffic → set mode: observe (remember to flip back to enforce after).

Validate:

python3 -c "import yaml,sys; yaml.safe_load(open('proxy/policy.yaml'))"

Hot-reload:
```
make restart-proxy
```
(Runs inside the Lima VM via the Makefile. If it fails because the VM is down, say so — make vm-up && make up first.)
Verify: check that legit traffic flows and blocks still fire:
```
make logs-blocked
```
For a domain just allowed, confirm it no longer appears in blocked logs when exercised. Suggest make test-block for a quick canary.
If mode was changed to observe, remind at the end: observe mode disables enforcement — flip back to enforce when profiling is done.

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.

6d ago First seen · 31 lines · 57 tokens per session scan A 04901da0ba07

Subscribe to this mod's changes

policy is a skill published in the GitHub repository thiagolmoraes/leash (5 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 334 once invoked, about $0.0003 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.

Security ai-agents claude-code falco llm-security mitmproxy network-monitoring

detecting-container-drift-at-runtime

Detect unauthorized modifications to running containers by monitoring for binary execution drift, file system changes, and configuration deviations from the original container image.

xalgorix/xalgorix · 34 tokens

integrate-arcjet-guard-genkit

Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…

arcjet/arcjet-js · 89 tokens

integrate-arcjet-guard-langchain

Integrate Arcjet security into a LangChain JS createAgent using @arcjet/guard — wrap tool() / StructuredTool, put guardMiddleware on createAgent({ middleware }) for MCP / unwrapped tools, and read configurable.threadid for correlation. Use when asked to add Arcjet to langchain createAgent, rate limit its tools, screen…

arcjet/arcjet-js · 101 tokens

integrate-arcjet-guard-langgraph

Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…

arcjet/arcjet-js · 87 tokens

integrate-arcjet-guard-google-adk

Integrate Arcjet security into a Google ADK JS app using @arcjet/guard — put guardPlugin first on Runner({ plugins }) so beforeToolCallback gates tools, and read a caller-owned id from helper options or context. Use when asked to add Arcjet to Google ADK, @google/adk, rate limit its tools, screen inbound messages, or…

arcjet/arcjet-js · 111 tokens

integrate-arcjet-guard-tanstack-ai

Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…

arcjet/arcjet-js · 103 tokens

leash: Skill for Claude Code