agentmods.dev

clawops: Skill for Claude Code

.claude/skills/audit-egress/SKILL.md

audit-egress is a skill for Claude Code from dfridkin/clawops. It costs 0 tokens per session (371 once invoked), scanned A, original, MPL-2.0.

A source-code review procedure for finding and checking outbound network calls, such as HTTP requests, SSH connections, cloud clients, and infrastructure providers.

In plain words
What is it for?
Use it before a pull request adds network calls, while adding providers or MCP tools, or during a security review.
Why use it?
It reveals missing cancellation controls, unsafe credential handling, undocumented connections, and MCP tools that do not declare external access correctly.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is dfridkin/clawops's own configuration. It tells Claude Code how to work on clawops itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything clawops configures →

not rated 6repo changed 1mo ago A scan 0 tokens original MPL-2.0
View source ↗ dfridkin/clawops clawops.fyi
Reuse

Borrowing it

Nothing to install: this file belongs to dfridkin/clawops. 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/dfridkin/clawops/main/.claude/skills/audit-egress/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dfridkin/clawops

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.

agentmods badge for audit-egress

README.md
[![agentmods](https://agentmods.dev/badge/skills/dfridkin/clawops/audit-egress/github.svg)](https://agentmods.dev/skills/dfridkin/clawops/audit-egress)
Your own site
<a href="https://agentmods.dev/skills/dfridkin/clawops/audit-egress"><img src="https://agentmods.dev/badge/skills/dfridkin/clawops/audit-egress/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.

agentmods 80×15 button for audit-egress

Your own site · 80×15
<a href="https://agentmods.dev/skills/dfridkin/clawops/audit-egress"><img src="https://agentmods.dev/badge/skills/dfridkin/clawops/audit-egress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 371 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00371
Opus 5.5 $0.00000 $0.00148
Sonnet 5.5 $0.00000 $0.00074
Haiku 4.5 $0.00000 $0.00037

Measured 1mo ago against content hash f3dd8282ada4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit-egress 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 1mo 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/audit-egress/SKILL.md · 39 lines

What it actually says

/audit-egress

Audit all outbound network calls in a source file or module.

Steps

  1. Scan for outbound calls in the target file(s):

    • fetch(, axios., http.request(, https.request(
    • ssh2 connect( calls
    • AWS SDK, GCP SDK, Azure SDK client instantiation
    • Pulumi provider resource creation

  2. For each call, verify:

    • It goes through an AbortSignal (R13)
    • Credentials come from process.env, not function arguments (R6)
    • The call is documented in the file's module header

  3. Check MCP tools additionally:

    • Does the tool set openWorldHint: true if it makes external calls?
    • Is the output trimmed to 8KB before returning (R14)?

  4. Check the destination is documented. Every host clawops or a deployed box reaches must appear in docs/security/egress.md, with when it is needed and what the failure looks like when it is blocked. An undocumented destination is one an operator with a deny-all network cannot allow, and they find out from a broken deployment rather than from a doc.

  5. Report findings as a structured list:

    [PASS] src/transport/ssh.ts:42 — AbortSignal present ✓
[FAIL] src/providers/aws/index.ts:17 — missing AbortSignal

When to run

  • Before submitting a PR that adds network calls
  • When a new outbound destination is introduced — ClawHub in 2.0 was one
  • When the /add-provider or /mcp-tool skill is used
  • During security review
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. 1mo ago Changed · +6 lines f3dd8282ada4
  2. 2mo ago First seen · 33 lines · 0 tokens per session scan A f1a9983fa049

Subscribe to this mod's changes

audit-egress is a skill published in the GitHub repository dfridkin/clawops (6 stars, last pushed today), licensed MPL-2.0. It costs nothing until one of its globs matches a file; then it loads 371 tokens. 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.

Securityagent-infrastructureai-agentsawsazureclaudecli
Related

audit-egress compared with skills from other repositories

audit-egress next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
audit-egressdfridkin/clawopsSkill6todayMPL-2.0A0Claude Code
aws-clielasticdotventures/_b00t_Skill1512d agononeA31Claude Code
notionArvo-AI/auroraSkill454yesterdayApache-2.0A23Claude Code
aws-essentialsericrisco/rsc-harnessSkill5032d agoMITA89Claude Code, Codex
dynamodbericrisco/rsc-harnessSkill5032d agoMITA82Claude Code, Codex
scalewayArvo-AI/auroraSkill454yesterdayApache-2.0A29Claude Code
ak-cloud-deployyaalalabs/agent-kernelSkill192yesterdayApache-2.0A177Claude Code, Codex