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.
npx agentmods add agents/random6913/claude-code-superkit/audit-botsgit clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkitWrote 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/agents/random6913/claude-code-superkit/audit-bots)<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>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 | $0.00022 | $0.00834 |
| Opus 5 | $0.00011 | $0.00417 |
| Sonnet 5 | $0.00004 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00083 |
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.
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:
CLAUDE.mdorAGENTS.md— project conventionsdocs/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.Sprintfwith UUID concat → FAIL (likely exceeds 64 bytes)
4. Stale Keyboard Cleanup
Find callback handlers. Check each:
- Calls
AnswerCallbackQuery(oranswerCallback()) — 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).
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.
- yesterday First seen · 88 lines · 22 tokens per session scan A f2d50167341f
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.
Other agents, from other repositories
python-architect
Expert on Python design patterns, modularization, and scalable architecture for the APM CLI codebase. Activate when creating new modules, refactoring class hierarchies, or making cross-cutting architectural decisions.
serena
Serena gives an agent LSP-backed navigation over this repo's Go code: find a symbol, find its references, replace its body.
bwk
Go specialist sub-agent. Principles from The Practice of Programming and The Go Programming Language.
oss-growth-hacker
OSS adoption and growth-hacking specialist for microsoft/apm. Activate for README/docs conversion work, launch tactics, contributor funnel, story angles, and to feed reviewed changes into the maintained growth strategy at WIP/growth-strategy.md.
apm-primitives-architect
Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…
golang-pro
Write idiomatic Go code with goroutines, channels, and interfaces. Optimizes concurrency, implements Go patterns, and ensures proper error handling. Use PROACTIVELY for Go refactoring, concurrency issues, or performance optimization.