debug-mode

A debug mode for AgentDev sessions that records tool calls, skill activations, hooks, and agent delegations in JSONL files. JSONL is a text format with one JSON record per line.

In plain words
What is it for?
Use it to enable, disable, and manage project-level debugging through `.claude/agentdev-debug.json`, choosing minimal, standard, or verbose event capture.
Why use it?
It makes agent behaviour and session performance easier to inspect after something goes wrong or needs improvement.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/madappgang/claude-code/debug-mode
Any agent
npx skills add MadAppGang/claude-code --skill debug-mode
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,914 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 4 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.02914
Opus 5 $0.00026 $0.01457
Sonnet 5 $0.00010 $0.00583
Haiku 4.5 $0.00005 $0.00291

Measured 2d ago against content hash eaa47c614ec7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

debug-mode scanned grade D with 4 findings 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 2d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST -d "$line" https://logging.example.com/ingest

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat > .claude/agentdev-debug.json << 'EOF'

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf claude-code-session-debug/

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST -d "$line" https://logging.example.com/ingest
plugins/agentdev/skills/debug-mode/SKILL.md · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

plugin: agentdev updated: 2026-01-20

AgentDev Debug Mode

Debug mode captures detailed session information for analysis, debugging, and optimization. All events are recorded to a JSONL file in claude-code-session-debug/.

Configuration

Debug mode uses per-project configuration stored in .claude/agentdev-debug.json.

Config File Format

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 active
  • level: string - Debug level (minimal, standard, verbose)
  • created_at: string - ISO timestamp when config was created

Enabling Debug Mode

Use 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

Debug Levels

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.

Changing Debug Level

Using jq:

jq '.level = "verbose"' .claude/agentdev-debug.json > tmp.json && mv tmp.json .claude/agentdev-debug.json

Output Location

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

JSONL Format

Each line in the JSONL file is a complete JSON event object. This append-only format is:

  • Crash-resilient (no data loss on unexpected termination)
  • Easy to process with jq
  • Streamable during the session

Event Schema (v1.0.0)

Read the full file on GitHub · 399 lines

Changes

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.

  1. 2d ago First seen · 399 lines · 51 tokens per session scan D eaa47c614ec7

Subscribe to this mod's changes

debug-mode is a skill published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 2,914 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 4 findings (sends data to an external url, reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens