CCA-F start here · Trap gym

Trap gym: all 30 exam traps

The exam's questions are easy to read. The hard part is the answers: every wrong option is a sensible practice that is wrong here. Below is every trap the exam guide sets up, each with the one-line rule that beats it. Open a trap to change the setting yourself in a simulator, watch what happens, then try exam-style questions.

Most traps come down to one of three mistakes: the right idea at the wrong layer, fixing the symptom instead of the cause, or the right content in the wrong home. Learn to spot them and you can rule out two options on most questions.

Jump to: D1 D2 D3 D4 D5 · 28 simulator pages cover 30 of 30 traps.

D1 Agentic Architecture & Orchestration

1
Stop reason simulatorGuide 1.1

Keep the loop going while stop_reason is "tool_use" and stop when it is "end_turn"; never stop because of the reply's wording or an iteration cap.

2
Coordinator split simulatorGuide 1.2

If whole topics are missing from the result and every subagent did its job, the coordinator split the task too narrowly, so fix the coordinator, not the subagents.

3
Subagent context simulatorGuide 1.3

A subagent knows only what its prompt tells it, so pass findings and sources explicitly, and launch parallel subagents as several Task calls in one response.

4
Prompt or hook simulatorGuide 1.4 and 1.5

A rule that must hold every time, like verifying identity before a refund, goes in a hook or gate; a preference can stay in the prompt.

5
Hook to clean up data simulatorGuide 1.5

Use a PostToolUse hook to tidy mixed formats, such as dates and status codes, before Claude sees the result, instead of asking Claude to do it.

6
Fixed chain or Claude decides simulatorGuide 1.6

If the steps are known in advance, use a fixed chain of prompts; let Claude choose the steps only when they depend on what is found along the way.

7
Resume, fork or start fresh simulatorGuide 1.7

Resume when nothing has changed, fork to try another approach from the same starting point, and start a new session with a summary when the earlier tool results are out of date.

D2 Tool Design & MCP Integration

8
Tool picker simulatorGuide 2.1

If Claude picks the wrong tool, first improve the tool descriptions (what each does, its inputs, its edge cases, when not to use it) before adding routers or new tools.

9
Tool failure simulatorGuide 2.2 and 5.3

Return a structured error that says what failed and whether a retry can help; never return an empty success, a generic "failed" or a crash.

10
Too many tools simulatorGuide 2.3

Give each agent the 4 or 5 tools its job needs, not all 18, with a small shared tool only for a need that comes up often.

11
tool_choice simulatorGuide 2.3 and 4.3

tool_choice set to "auto" lets Claude choose between text and a tool, "any" forces it to call some tool, and naming one tool forces that exact tool, for example to run extraction first.

12
MCP: where and what simulatorGuide 2.4

A server the team shares goes in the project .mcp.json with secrets written as ${VAR}, a personal or experimental one goes in your user config, and Claude gets a tool for things it must do and a resource for things it must read.

13
Built-in tools simulatorGuide 2.5

Use Grep to search inside files and Glob to find files by name pattern, use Edit for a small targeted change, and when Edit fails because the text appears more than once, Read the whole file and Write it back.

D3 Claude Code Configuration & Workflows

14
Where an instruction lives simulatorGuide 3.1 and 3.2 and 3.3

Team rules go in the project CLAUDE.md, personal ones in ~/.claude/CLAUDE.md, rules for one kind of file spread across folders in .claude/rules with paths, a task you start yourself in a command, and a long procedure needed only sometimes in a skill.

15
Plan or just do it simulatorGuide 3.4

Make a small, settled change directly; use plan mode for big, many-file or undecided changes, and send long searches to the Explore subagent.

16
Examples, tests first or interview simulatorGuide 3.5

Show concrete input and output examples for a transformation, write tests first when the right behaviour is known but fixes keep breaking cases, and let Claude interview you first when nobody has said exactly what's wanted.

17
Claude Code in CI simulatorGuide 3.6

In CI, run Claude Code with -p so it doesn't wait for input, use --output-format json with --json-schema for results a script can parse, and put the project's testing and review standards in CLAUDE.md.

D4 Prompt Engineering & Structured Output

18
Explicit criteria simulatorGuide 4.1

To cut false positives, give categorical criteria such as "flag a comment only when it contradicts the code"; telling Claude to "be conservative" or report "only high-confidence" findings doesn't raise precision.

19
Few-shot examples simulatorGuide 4.2

If the output is inconsistent or the ambiguous cases go wrong even with clear instructions, add 2 to 4 targeted examples that show the reasoning and the format, instead of writing longer instructions.

20
Schema and nullable fields simulatorGuide 4.3 and 4.4

A schema stops syntax errors but not wrong values, so make a field optional or nullable when the value may not be in the document, and retry with the specific error only when the information is actually there.

21
Retry with the error simulatorGuide 4.4

When an extraction fails a check, retry with the specific error attached, but don't retry when the value isn't in the document at all.

22
Batch or now simulatorGuide 4.5

Use the Batch API at half price only when nobody is waiting and no back-and-forth tool calls are needed; anything someone waits on, like a pre-merge check, calls the API directly.

23
Self-review simulatorGuide 4.6 and 3.6

Review with a separate Claude instance that didn't write the code, and review large changes file by file before one pass across all the files.

D5 Context Management & Reliability

24
Context meter simulatorGuide 5.1

Keep exact facts such as amounts, dates and promises in a case-facts block and trim tool results to the fields you need; a bigger context window or a running summary blurs the numbers.

25
Who escalates simulatorGuide 5.2

Escalate when the customer asks for a person, when there's a policy exception or gap, or when the agent can't make progress; never on sentiment or self-rated confidence.

26
Several customer matches simulatorGuide 5.2

When a lookup returns more than one customer, ask the person for an identifier such as an order number or email; never guess which one is meant.

27
Empty result or failure simulatorGuide 5.3 and 2.2

"No results" and "couldn't reach the system" are different answers: report a failure as a failure with what was tried, and an empty search as a valid empty result.

28
Large codebase simulatorGuide 5.4

In a long codebase exploration, save key findings to a scratchpad file, send verbose exploration to subagents, and use /compact when the context fills.

29
Confidence and sampling simulatorGuide 5.5

A high overall accuracy can hide one weak document type or field, so measure accuracy by type and field with stratified random samples before automating.

30
Sources simulatorGuide 5.6

Keep every claim linked to its source through the synthesis, and when two sources disagree, show both with their sources and dates instead of picking one.