8 traps that catch most candidates
Severity reflects how often the trap appears on the exam, not how dangerous the bug is in production. A high-severity trap here is one where the distractor is plausible enough to fool a prepared candidate.
| Pattern | Domain | Severity | Trap | Fix | Shows up in |
|---|---|---|---|---|---|
| Subagent context inheritance | D1 | high | Treating a subagent as if it inherits the parent's conversation history. It does not. The parent's tool results, prior turns, and system prompt are invisible until you pass them explicitly. | Pass everything the subagent needs in the task prompt: the goal, relevant facts, allowed tools, and return format. Treat each subagent invocation as a fresh session. | multi-agent-research-system ↗ |
| 18-tool degradation cliff | D2 | medium | Stacking 20+ tools on a single agent on the assumption that more capability is better. Selection accuracy degrades sharply past roughly 18 tools as descriptions blur in attention. | Cap tools per agent at ~18, or fan out to subagents with narrow tool whitelists. Each subagent does one job well; the coordinator routes. | agentic-tool-design ↗ |
| Bigger model for a design problem | Cross | high | Distractor offers a more capable model, more tokens, or higher temperature. The behavior issue is actually system design: weak tool descriptions, missing few-shot, undecomposed task. | Fix the architecture first. Improve tool descriptions, add canonical examples, decompose the task, structure the prompt. Only escalate model after design is sound. | Day-of distractor patterns ↗ |
| Prompt-tuned safety guardrails | D4 / D5 | high | Relying on a prompt instruction ("never do X") to enforce a compliance, financial, or security guarantee. Prompt enforcement lands around 70% - fine for ergonomics, fatal for stakes. | Use deterministic SDK hooks (PreToolUse / PostToolUse) for hard guarantees. Hooks land at ~100%. Prompts handle preference; hooks handle policy. | Day-of distractor patterns ↗ |
| Progressive summarization losing case facts | D5 | high | Auto-summarizing the entire conversation as it grows. Critical case-facts (account IDs, prior decisions, user constraints) compress away and the agent contradicts itself two turns later. | Pin a case-facts block that never gets summarized. Summarize chat history only. Keep the case-facts block at the start of every turn. | case-facts-block ↗ |
| Lost-in-the-middle | D5 | medium | Assuming the model attends evenly across a long context. Mid-context content is reliably under-weighted; key instructions placed in the middle get ignored. | Place critical instructions at the start and end. Repeat the most important rule at the end of the system prompt. Keep working context tight. | context-window ↗ |
| tool_use output without schema retry | D4 | medium | Trusting tool_use output to match your schema on the first call. JSON validation fails silently downstream and the agent appears to succeed. | Validate against a JSON schema. On failure, retry with the validation error in the next user message. Bound retries (2-3 max) and escalate. | structured-outputs ↗ |
| CLAUDE.md hierarchy confusion | D3 | low | Editing ~/.claude/CLAUDE.md and wondering why project-specific instructions don't apply, or vice versa. Precedence is layered, not flat. | Project-level overrides home. Subdirectory CLAUDE.md files cascade and override their parent. Check the resolved hierarchy with /memory before editing the wrong file. | claude-md-hierarchy ↗ |
The two patterns that decide the most exam questions
Once you internalise these two, you will recognise the answer-shape on a meaningful chunk of the mock from the distractor pattern alone. Both are documented from the public CCA-F study material plus the practice-bank misconception analysis surfaced by the adaptive plan.
Model vs Design
Distractor shape. Suggests a bigger model, more tokens, or a higher temperature.
Correct shape. Fixes system design: tool descriptions, few-shot examples, task decomposition, prompt structure.
Rule. Architecture first. Only escalate model after design is sound.
Prompt vs Hook
Distractor shape. Suggests adding instructions to the system prompt to enforce a safety / compliance / financial constraint.
Correct shape. Uses deterministic SDK hooks (PreToolUse / PostToolUse) - ~100% enforcement vs ~70% for prompt tuning.
Rule. If being wrong has real cost, the right answer involves a hook.
Per-rule single-page references
Each cheatsheet is a one-page rule lookup with selection table, pitfalls, and drill links. We add cheatsheets when exam-takers ask for them - not preemptively.
tool_choice
Domain D2
Decision cheatsheet for tool_choice - auto, any, or forced. When each mode applies and the pitfalls to avoid.
Open ↗Hooks vs CLAUDE.md
Reference
Decision cheatsheet for when to enforce a constraint with a hook vs. an instruction in CLAUDE.md - advisory context, guaranteed execution, and the CCA-F exam decision rule.
Open ↗Want a cheatsheet on a specific topic? Open an issue on the GitHub repo with the rule and your use-case.
Three downloadable cheatsheet posters
Each poster is a 1080x1920 painterly SVG that downloads as a 2160x3840 PNG. Print on A4 portrait, pin above your desk for the week before the exam, or save and reread 24 hours out.
8 Anti-Patterns
Cross-domain
Severity-coded list of the 8 canonical CCA-F traps with the actual fix.
Print and pin above your desk for the week before exam day.
Open + download ↗Distractor Patterns
Test strategy
The two test-taking traps that catch most candidates - decoded.
Read once, then re-read 24 hours before the exam.
Open + download ↗Domain Blueprint Map
Study planning
5 domains, blueprint weights, and the high-leverage concepts in each.
Use as a domain-by-domain study checklist.
Open + download ↗When to come here vs Concepts vs Scenarios
- Concepts answer what is X. Read once.
- Scenarios answer how do I build X. Read once or twice.
- Reference (this pillar) answers I need the rule right now. Open mid-mock, mid-build, or in the 24 hours before sitting.
The anti-patterns table above is the fastest pre-exam refresher we ship. Read it the morning of the exam and one of the eight will surface in your first ten questions.