audit-bots

audit-bots is an agent for Claude Code from RaNDoM6913/claude-code-superkit. It costs 22 tokens per session (834 once invoked), scanned A, original, MIT.

A production-readiness audit for Telegram bots that checks concurrency, shutdown handling, callback limits, stale keyboards, and related reliability risks.

In plain words
What is it for?
Use it to audit Go Telegram bots for goroutine cancellation, update-channel cleanup, callback-data size, keyboard cleanup, rate limits, and callback integrity.
Why use it?
It helps prevent leaks, broken callbacks, incomplete shutdowns, and other failures that may appear only in production.

Agent for Claude Code

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/random6913/claude-code-superkit/audit-bots
Clone the repo
git clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkit

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-bots

README.md
[![agentmods](https://agentmods.dev/badge/agents/random6913/claude-code-superkit/audit-bots.svg)](https://agentmods.dev/agents/random6913/claude-code-superkit/audit-bots)
Your own site
<a href="https://agentmods.dev/agents/random6913/claude-code-superkit/audit-bots"><img src="https://agentmods.dev/badge/agents/random6913/claude-code-superkit/audit-bots.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 834 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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.00834
Opus 5 $0.00011 $0.00417
Sonnet 5 $0.00004 $0.00167
Haiku 4.5 $0.00002 $0.00083

Measured yesterday against content hash f2d50167341f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-bots 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 yesterday.

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.

packages/showcase/.claude/agents/audit-bots.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bot Audit — SocialApp

Audit tgbots/bot_moderator/ and tgbots/bot_support/ for production safety and convention compliance.

Phase 0: Load Project Context

Read if exists:

  1. CLAUDE.md or AGENTS.md — project conventions
  2. docs/architecture/ — relevant architecture docs for the task at hand

Use this context to:

  • Know project-specific conventions and patterns
  • Identify documented rules to check with HIGH confidence
  • Understand the tech stack and framework in use

Checks

1. Goroutine Leak Risk

Grep go func in tgbots/. For each:

  • Check context.WithTimeout or ctx.Done() select exists inside the goroutine. FAIL if goroutine spawned without context cancellation.

2. Unclosed Update Channel

If GetUpdatesChan is used → check StopReceivingUpdates() in defer or shutdown hook. If ListenForWebhook → check HTTP server has Shutdown(ctx). WARN if graceful shutdown is missing.

3. Callback Data Length

Grep all NewInlineKeyboardButtonData calls. Estimate callback_data length:

  • String literal >50 chars → WARN (close to 64-byte TG limit)
  • fmt.Sprintf with UUID concat → FAIL (likely exceeds 64 bytes)

4. Stale Keyboard Cleanup

Find callback handlers. Check each:

  • Calls AnswerCallbackQuery (or answerCallback()) — FAIL if missing
  • Edits/removes keyboard after processing — WARN if keyboard left stale

5. Rate Limiting

Grep for loops sending messages: for.*bot\.Send|for.*tg\.Send. WARN if no rate.Limiter or time.Sleep in the loop. Check for 429/RetryAfter handling anywhere in bot code.

6. Direct DB Writes (Moderator Bot)

In tgbots/bot_moderator/, grep for direct SQL (pool.Exec|pool.Query|pool.QueryRow). FAIL if approve/reject actions write directly to DB (should use adminhttp API client).

7. Error Handling Specificity

Grep bot.Send|bot.Request|tg.Send calls. Check if errors are type-asserted to *tgbotapi.Error. WARN if errors handled generically without checking Telegram error codes (403/429/400).

Read the full file on GitHub · 88 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. yesterday First seen · 88 lines · 22 tokens per session scan A f2d50167341f

Subscribe to this mod's changes

audit-bots is an agent published in the GitHub repository RaNDoM6913/claude-code-superkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 834 once invoked, about $0.0001 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 2026-09-03.

Related

Other agents, from other repositories