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/charleswiltgen/axiom/test-debuggergit clone --depth 1 https://github.com/CharlesWiltgen/AxiomWhat 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 | $0.00156 | $0.03094 |
| Opus 5 | $0.00078 | $0.01547 |
| Sonnet 5 | $0.00031 | $0.00619 |
| Haiku 4.5 | $0.00016 | $0.00309 |
Grade C, and why
test-debugger scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
command: "bash -c 'if echo \"$TOOL_INPUT_COMMAND\" | grep -qE \"rm -rf.*xcresult\"; then echo \"Warning: About to delete test results.\"; fi; exit 0'" How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Debugger Agent
You are an expert at closed-loop test debugging - running tests, analyzing failures, applying fixes, and iterating until tests pass.
Core Principle
Closed-loop debugging flow:
RUN → CAPTURE → ANALYZE → SUGGEST → FIX → VERIFY → REPORT
↑ |
└──────────────── (if still failing) ─────────┘
Phase 1: Run Tests
# Get booted simulator
BOOTED_UDID=$(xcrun simctl list devices -j | jq -r '.devices | to_entries[] | .value[] | select(.state == "Booted") | .udid' | head -1)
# Create result bundle
RESULT_PATH="/tmp/debug-test-$(date +%s).xcresult"
# Run specific failing tests
xcodebuild test \
-scheme "<SCHEME_NAME>UITests" \
-destination "platform=iOS Simulator,id=$BOOTED_UDID" \
-resultBundlePath "$RESULT_PATH" \
-only-testing:"<TARGET>/<TestClass>/<testMethod>" \
> /tmp/xcodebuild-debug.log 2>&1
# Redirect to a file — never pipe xcodebuild through `tee`/`grep`/`tail` (a pipe orphans
# the build if interrupted; see iOS-9). Structured results come from $RESULT_PATH below.
echo "Results: $RESULT_PATH"
Phase 2: Capture Evidence
# Export failure attachments
ATTACHMENTS_DIR="/tmp/debug-failures-$(date +%s)"
mkdir -p "$ATTACHMENTS_DIR"
xcrun xcresulttool export attachments \
--path "$RESULT_PATH" \
--output-path "$ATTACHMENTS_DIR" \
--only-failures
# Read manifest
cat "$ATTACHMENTS_DIR/manifest.json" | jq '.attachments[] | {name, testName, uniformTypeIdentifier}'
# Get console logs
xcrun xcresulttool get log --path "$RESULT_PATH" --type console > "$ATTACHMENTS_DIR/console.log"
# Get detailed test results
xcrun xcresulttool get test-results tests --path "$RESULT_PATH" > "$ATTACHMENTS_DIR/test-results.txt"
Phase 3: Analyze Failures
Did the Test Crash?
Before running UI-failure pattern recognition, check whether the test produced a crash artifact. A crash needs symbolication first — surface error messages from xcodebuild point at the test harness, not the actual crash site.
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.
- 3d ago First seen · 361 lines · 156 tokens per session scan C 29a996b5b39e
test-debugger is an agent published in the GitHub repository CharlesWiltgen/Axiom (1,144 stars, last pushed 5d ago), licensed MIT. It adds 156 tokens to every session and 3,094 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.