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 commands/madappgang/claude-code/debug-enablegit clone --depth 1 https://github.com/MadAppGang/claude-codeWhat 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 | $0.00029 | $0.00695 |
| Opus 5 | $0.00015 | $0.00347 |
| Sonnet 5 | $0.00006 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade C, and why
debug-enable scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 700 claude-code-session-debug Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > .claude/agentdev-debug.json << 'EOF' How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enable Debug Mode
Enable agentdev debug mode to capture detailed session information. Uses per-project configuration stored in .claude/agentdev-debug.json.
Instructions
- Create the
.claude/directory if it does not exist - Create or update
.claude/agentdev-debug.jsonwith enabled: true - Create the debug output directory
- Confirm debug mode is enabled
Implementation
Execute the following steps:
# Create .claude directory if needed
mkdir -p .claude
# Create or update agentdev-debug.json config
cat > .claude/agentdev-debug.json << 'EOF'
{
"enabled": true,
"level": "standard",
"created_at": "TIMESTAMP_PLACEHOLDER"
}
EOF
# Replace timestamp placeholder with actual ISO timestamp
if command -v jq &> /dev/null; then
TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
jq --arg ts "$TIMESTAMP" '.created_at = $ts' .claude/agentdev-debug.json > .claude/agentdev-debug.json.tmp
mv .claude/agentdev-debug.json.tmp .claude/agentdev-debug.json
else
# Fallback without jq - use sed
TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
sed -i.bak "s/TIMESTAMP_PLACEHOLDER/$TIMESTAMP/" .claude/agentdev-debug.json
rm -f .claude/agentdev-debug.json.bak
fi
# Create debug output directory with secure permissions
mkdir -p claude-code-session-debug
chmod 700 claude-code-session-debug
# Confirm setup
echo "=== Debug Mode Enabled ==="
echo ""
echo "Config file: $(pwd)/.claude/agentdev-debug.json"
cat .claude/agentdev-debug.json
echo ""
echo "Debug directory: $(pwd)/claude-code-session-debug/"
Debug Levels
You can change the debug level by editing .claude/agentdev-debug.json:
minimal- Phase transitions, errors, session start/endstandard- All of minimal + tool invocations, agent delegations (default)verbose- All of standard + skill activations, hook triggers, full parameters
To change level:
# Using jq
jq '.level = "verbose"' .claude/agentdev-debug.json > tmp.json && mv tmp.json .claude/agentdev-debug.json
# Or manually edit .claude/agentdev-debug.json
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.
- 2d ago First seen · 98 lines · 29 tokens per session scan C 64defc758c11
debug-enable is a command published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 695 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.