plugins/agentdev/skills/debug-mode/SKILL.md
Manages agentdev debug mode — records tool, skill, hook, and agent events to JSONL. Use when debugging agent behavior, optimizing workflows, or analyzing session performance.
npx skillsauth add madappgang/magus debug-modeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
plugin: agentdev updated: 2026-01-20
Debug mode captures detailed session information for analysis, debugging, and optimization.
All events are recorded to a JSONL file in claude-code-session-debug/.
Debug mode uses per-project configuration stored in .claude/agentdev-debug.json.
Location: .claude/agentdev-debug.json (in project root)
{
"enabled": true,
"level": "standard",
"created_at": "2026-01-09T07:00:00Z"
}
Fields:
enabled: boolean - Whether debug mode is activelevel: string - Debug level (minimal, standard, verbose)created_at: string - ISO timestamp when config was createdUse the command to create the config file:
/agentdev:debug-enable
This creates .claude/agentdev-debug.json with enabled: true.
Or manually create the file:
mkdir -p .claude
cat > .claude/agentdev-debug.json << 'EOF'
{
"enabled": true,
"level": "standard",
"created_at": "2026-01-09T07:00:00Z"
}
EOF
| Level | Captured Events |
|-------|-----------------|
| minimal | Phase transitions, errors, session start/end |
| standard | All of minimal + tool invocations, agent delegations |
| verbose | All of standard + skill activations, hook triggers, full parameters |
Default level is standard.
Using jq:
jq '.level = "verbose"' .claude/agentdev-debug.json > tmp.json && mv tmp.json .claude/agentdev-debug.json
Debug sessions are saved to:
claude-code-session-debug/agentdev-{slug}-{timestamp}-{id}.jsonl
Example:
claude-code-session-debug/agentdev-graphql-reviewer-20260109-063623-ba71.jsonl
Each line in the JSONL file is a complete JSON event object. This append-only format is:
jq{
"event_id": "550e8400-e29b-41d4-a716-446655440001",
"correlation_id": null,
"timestamp": "2026-01-09T06:40:00Z",
"type": "tool_invocation",
"data": { ... }
}
Fields:
event_id: Unique UUID for this eventcorrelation_id: Links related events (e.g., tool_invocation -> tool_result)timestamp: ISO 8601 timestamptype: Event type (see below)data: Type-specific payload| Type | Description |
|------|-------------|
| session_start | Session initialization with metadata |
| session_end | Session completion |
| tool_invocation | Tool called with parameters |
| tool_result | Tool execution result |
| skill_activation | Skill loaded by agent |
| hook_trigger | PreToolUse/PostToolUse hook fired |
| agent_delegation | Task delegated to sub-agent |
| agent_response | Sub-agent returned result |
| phase_transition | Workflow phase changed |
| user_interaction | User approval/input requested |
| proxy_mode_request | External model request via Claudish |
| proxy_mode_response | External model response |
| error | Error occurred |
Debug mode automatically sanitizes sensitive data:
Redacted Patterns:
sk-*, ghp_*, AKIA*, etc.)xox*)AIza*)Install jq for JSON processing:
# macOS
brew install jq
# Linux
apt-get install jq
# Count events by type
cat session.jsonl | jq -s 'group_by(.type) | map({type: .[0].type, count: length})'
# Tool invocation counts
cat session.jsonl | jq -s '
[.[] | select(.type == "tool_invocation") | .data.tool_name]
| group_by(.)
| map({tool: .[0], count: length})
| sort_by(-.count)'
# Find all errors and failed tool results
cat session.jsonl | jq 'select(.type == "error" or (.type == "tool_result" and .data.success == false))'
# Chronological event summary
cat session.jsonl | jq '"\(.timestamp) [\(.type)] \(.data | keys | join(", "))"'
# Find tool invocation and its result
INVOCATION_ID="550e8400-e29b-41d4-a716-446655440001"
cat session.jsonl | jq "select(.event_id == \"$INVOCATION_ID\" or .correlation_id == \"$INVOCATION_ID\")"
# Calculate time between phase transitions
cat session.jsonl | jq -s '
[.[] | select(.type == "phase_transition")]
| sort_by(.timestamp)
| .[]
| {phase: .data.to_name, timestamp: .timestamp}'
# Find slowest agent delegations
cat session.jsonl | jq -s '
[.[] | select(.type == "agent_response")]
| sort_by(-.data.duration_ms)
| .[:5]
| .[]
| {agent: .data.agent, duration_sec: (.data.duration_ms / 1000)}'
# External model response times
cat session.jsonl | jq -s '
[.[] | select(.type == "proxy_mode_response")]
| .[]
| {model: .data.model_id, success: .data.success, duration_sec: (.data.duration_ms / 1000)}'
Use the command:
/agentdev:debug-disable
Or manually update:
jq '.enabled = false' .claude/agentdev-debug.json > tmp.json && mv tmp.json .claude/agentdev-debug.json
Or delete the config file:
rm -f .claude/agentdev-debug.json
rm -rf claude-code-session-debug/
find claude-code-session-debug/ -name "*.jsonl" -mtime +7 -delete
find claude-code-session-debug/ -name "*.jsonl" -size +10M -delete
Debug files are created with restrictive permissions:
0o700 (owner only)0o600 (owner read/write only)This prevents other users from reading potentially sensitive session data.
{"event_id":"init-1736408183","timestamp":"2026-01-09T06:36:23Z","type":"session_start","data":{"schema_version":"1.0.0","session_id":"agentdev-graphql-reviewer-20260109-063623-ba71","user_request":"Create an agent that reviews GraphQL schemas","session_path":"ai-docs/sessions/agentdev-graphql-reviewer-20260109-063623-ba71","environment":{"claudish_available":true,"plugin_version":"1.4.0","jq_available":true}}}
{"event_id":"550e8400-e29b-41d4-a716-446655440001","timestamp":"2026-01-09T06:36:25Z","type":"tool_invocation","data":{"tool_name":"TodoWrite","parameters":{"todos":"[REDACTED]"},"context":{"phase":0,"agent":null}}}
{"event_id":"550e8400-e29b-41d4-a716-446655440002","correlation_id":"550e8400-e29b-41d4-a716-446655440001","timestamp":"2026-01-09T06:36:25Z","type":"tool_result","data":{"tool_name":"TodoWrite","success":true,"result_size_bytes":156,"duration_ms":12}}
{"event_id":"550e8400-e29b-41d4-a716-446655440003","timestamp":"2026-01-09T06:36:26Z","type":"phase_transition","data":{"from_phase":null,"to_phase":0,"from_name":null,"to_name":"Init","transition_reason":"completed","quality_gate_result":true}}
{"event_id":"550e8400-e29b-41d4-a716-446655440004","timestamp":"2026-01-09T06:36:30Z","type":"agent_delegation","data":{"target_agent":"agentdev:architect","prompt_preview":"SESSION_PATH: ai-docs/sessions/agentdev-graphql-reviewer...","prompt_length":1456,"proxy_mode":null,"session_path":"ai-docs/sessions/agentdev-graphql-reviewer-20260109-063623-ba71"}}
{"event_id":"end-1736408565","timestamp":"2026-01-09T06:42:45Z","type":"session_end","data":{"success":true}}
Check if debug mode is enabled:
/agentdev:debug-status
Verify config file:
cat .claude/agentdev-debug.json
Verify the directory is writable:
ls -la claude-code-session-debug/
brew install jq or apt-get install jqhead -1 session.jsonl | jq .
Debug files can grow large in verbose mode. Use minimal level for lighter capture:
Update config:
jq '.level = "minimal"' .claude/agentdev-debug.json > tmp.json && mv tmp.json .claude/agentdev-debug.json
Or clean up old files regularly:
find claude-code-session-debug/ -name "*.jsonl" -mtime +3 -delete
The JSONL format works with JSON syntax highlighting. For better viewing:
# Convert to CSV for spreadsheet import
cat session.jsonl | jq -rs '
(.[0] | keys_unsorted) as $keys
| ($keys | @csv),
(.[] | [.[$keys[]]] | @csv)' > session.csv
# Tail and send to logging service
tail -f session.jsonl | while read line; do
curl -X POST -d "$line" https://logging.example.com/ingest
done
| Command | Description |
|---------|-------------|
| /agentdev:debug-enable | Enable debug mode (creates config file) |
| /agentdev:debug-disable | Disable debug mode (updates config file) |
| /agentdev:debug-status | Check current debug mode status |
testing
A test skill for validation testing. Use when testing skill parsing and validation logic.
tools
--- name: bad-skill description: This skill has invalid YAML in frontmatter allowed-tools: [invalid, array, syntax prerequisites: not-an-array --- # Bad Skill This skill has malformed frontmatter that should fail parsing. The YAML has: - Unclosed array bracket - Wrong type for prerequisites (should be array, not string)
development
Sync model aliases from the curated Firebase database. Fetches default model assignments, short aliases, team compositions, and known model metadata from the claudish API. Run this to get fresh model recommendations.
tools
Release one or more Magus plugins to the distribution repos (magus, magus-alpha, magus-marketing). Handles version inference from git history, marketplace.json updates, tagging, and force-push to lean dist repos. Use whenever the user says "release kanban", "release the dev plugin", "cut a new version of gtd", "bump kanban to 1.7", or hands you a batch like "release kanban and gtd". Also use for multi-plugin releases and for checking what a release would contain before committing.