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 skills add ronmkr/PromptBook --skill agent-architecture-auditgit clone --depth 1 https://github.com/ronmkr/PromptBookWrote 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/ronmkr/promptbook/agent-architecture-audit)<a href="https://agentmods.dev/skills/ronmkr/promptbook/agent-architecture-audit"><img src="https://agentmods.dev/badge/skills/ronmkr/promptbook/agent-architecture-audit/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/ronmkr/promptbook/agent-architecture-audit"><img src="https://agentmods.dev/badge/skills/ronmkr/promptbook/agent-architecture-audit.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 | $0.00070 | $0.02301 |
| Opus 5 | $0.00035 | $0.01151 |
| Sonnet 5 | $0.00014 | $0.00460 |
| Haiku 4.5 | $0.00007 | $0.00230 |
Grade A, and why
agent-architecture-audit 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 7d 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.
This is a copy
95% identical to agent-architecture-audit — 30 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Architecture Audit
A diagnostic workflow for agent systems that hide failures behind wrapper layers, stale memory, retry loops, or transport/rendering mutations.
When to Activate
MANDATORY for:
- Releasing any agent or LLM-powered application to production
- Shipping features with tool calling, memory, or multi-step workflows
- Agent behavior degrades after adding wrapper layers
- User reports "the agent is getting worse" or "tools are flaky"
- Same model works in playground but breaks inside your wrapper
- Debugging agent behavior for more than 15 minutes without finding root cause
Especially critical when:
- You've added new prompt layers, tool definitions, or memory systems
- Different agents in your system behave inconsistently
- The model was fine yesterday but is hallucinating today
- You suspect hidden repair/retry loops silently mutating responses
Do not use for:
- General code debugging — use
agent-introspection-debugging - Code review — use language-specific reviewer agents
- Security scanning — use
security-revieworsecurity-review/scan - Agent performance benchmarking — use
agent-eval - Writing new features — use the appropriate workflow skill
The 12-Layer Stack
Every agent system has these layers. Any of them can corrupt the answer:
| # | Layer | What Goes Wrong |
|---|---|---|
| 1 | System prompt | Conflicting instructions, instruction bloat |
| 2 | Session history | Stale context injection from previous turns |
| 3 | Long-term memory | Pollution across sessions, old topics in new conversations |
| 4 | Distillation | Compressed artifacts re-entering as pseudo-facts |
| 5 | Active recall | Redundant re-summary layers wasting context |
| 6 | Tool selection | Wrong tool routing, model skips required tools |
| 7 | Tool execution | Hallucinated execution — claims to call but doesn't |
| 8 | Tool interpretation | Misread or ignored tool output |
| 9 | Answer shaping | Format corruption in final response |
| 10 | Platform rendering | Transport-layer mutation (UI, API, CLI mutates valid answers) |
| 11 | Hidden repair loops | Silent fallback/retry agents running second LLM pass |
| 12 | Persistence | Expired state or cached artifacts reused as live evidence |
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.
- 7d ago First seen · 257 lines · 70 tokens per session scan A 7cdb45db4e7f
agent-architecture-audit is a skill published in the GitHub repository ronmkr/PromptBook (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 2,301 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to agent-architecture-audit, differing in 30 lines, and is treated as a copy.
Other skills, from other repositories
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
optimization
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
triage
Diagnose and fix broken MCP servers in mcptoon — doctor, health, per-server probes, and the common failure playbook.
arkcli-doctor
A diagnostic tool for ARK services, accounts, models, and inference endpoints. An inference endpoint is the online address through which an AI model receives requests.
pi-observability-local-dev
Use when developing or reviewing packages/pi-observability dashboard/server changes locally, especially rebuilding dist, restarting the 43190 server, validating UI behavior, or keeping the local dashboard in sync with source edits.