Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
SkillScore95Maintained
Automatic
◆AI Engineer pack
Last verified 8/8/2026
What it changes
Passed 20 of 21 test cases with the skill, and 14 of 21 without it.
Without skill68%
With skill95%
Checks it passed that the model alone missed
The fix plan is formatted under the key ordered_fix_plan
Each fix plan object contains the keys order, goal, why_now, and expected_effect
The overall health key is named overall_health rather than risk_score or health_rating
and 6 more in the full report
7 fixed14 passed either way0 still failing1 broke
Pass-rate lift
+27 pp
Tokens
+89%
Agent turns
0%
Response time
-27%
Model gemini-3.6-flashMeasured 8/8/2026v121 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
Perform a static security vulnerability scan on our Python FastAPI service to detect SQL injection hazards, hardcoded secrets, and unsafe deserialization calls in `app/routers/auth.py`.
What was checked, without and with the skill
Checked
Without skill
With skill
The response focuses on static code security analysis and vulnerability detection without utilizing the agent architecture audit workflow
Missed
Passed
case-22 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md249 linessingle file
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-review or security-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