Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsnpx agentmods add skills/calle-ai/awesome-phone-call-agents/auditlaneWrote 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.
[](https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/auditlane)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/auditlane"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/auditlane/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.
<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/auditlane"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/auditlane.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00032 | $0.02253 |
| Opus 5.5 | $0.00013 | $0.00901 |
| Sonnet 5.5 | $0.00006 | $0.00451 |
| Haiku 4.5 | $0.00003 | $0.00225 |
Grade D, and why
auditlane scanned grade D with 3 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
(`curl | bash`), infrastructure (terraform/kubectl/docker/cloud CLIs), Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
exact JSON](https://github.com/soujasK/AuditLane/blob/main/.claude/settings.json), Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(`curl | bash`), infrastructure (terraform/kubectl/docker/cloud CLIs), How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AuditLane skill
Full source: github.com/soujasK/AuditLane — everything below assumes you've cloned it:
git clone https://github.com/soujasK/AuditLane
cd AuditLane
The actual problem this solves
Autonomous agents increasingly get real execution access — shell commands, infrastructure changes, database access — through hooks, MCP servers, and CI pipelines. A common mitigation is "the agent should ask a human before doing anything dangerous." That's an honor system. A careless, confused, or compromised agent just doesn't ask, and nothing stops it.
This reference explores placing a supplementary check at a host's
pre-execution hook. The linked implementation targets Claude Code's
PreToolUse hook for configured Bash tools; read the
host and safety notes before installation.
It is an experimental pattern matcher, not an unskippable security boundary:
nonmatching commands and other execution paths can bypass this check, and
dress-rehearsal fixtures can produce an allow response without a real call.
Keep independent human authorization and host permissions in place for real
destructive actions. A phone interpretation alone must not authorize them.
What it actually does
1. telephony-gate — experimental command-pattern hook
auditlane/danger_patterns.py pattern-matches the command against 22
categories across databases, filesystem, remote-code-execution
(curl | bash), infrastructure (terraform/kubectl/docker/cloud CLIs),
git, system control, and package publishing. A match calls the
configured authorizer with a free-recall-first interview ("what did you
discuss/approve regarding X?" before reading back the specific claim —
this is the same reason real witness interviews lead with open recall,
not a leading yes/no). The hook uses heuristic confirmation results to propose
an allow/deny decision; rehearsal uses fictional responses. Nonmatching commands
pass through without a verification call. Neither behavior establishes that a
command is safe or that all risky execution paths were covered.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 212 lines · 32 tokens per session scan D 551bfcd1ce25
auditlane is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 2,253 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-16.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…