debug

debug is a command for coding agents from synaptiai/synapti-marketplace. It costs 20 tokens per session (2,367 once invoked), scanned A, original, Apache-2.0.

A guided debugging command that investigates an issue by collecting evidence, testing possible causes, applying a fix, and checking the result.

In plain words
What is it for?
Use it to investigate failing code, examine recent changes and repository state, test hypotheses, and validate fixes.
Why use it?
It helps replace guesswork with a structured search for the underlying cause of a bug.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the flow plugin — 31 skills, 21 commands, 9 agents shipped together

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 commands/synaptiai/synapti-marketplace/debug
Clone the repo
git clone --depth 1 https://github.com/synaptiai/synapti-marketplace

Or install flow, the plugin that ships this one along with the rest of its 31 skills, 21 commands, 9 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for debug

README.md
[![agentmods](https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/debug.svg)](https://agentmods.dev/commands/synaptiai/synapti-marketplace/debug)
Your own site
<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/debug"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00020 $0.02367
Opus 5 $0.00010 $0.01184
Sonnet 5 $0.00004 $0.00473
Haiku 4.5 $0.00002 $0.00237

Measured yesterday against content hash bbf985a32b6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug scanned grade A with 0 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/flow/commands/debug.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug: $ARGUMENTS

Structured debugging with root cause analysis. Follows Explore > Plan > Code > Verify loop.

Required Skills

This command operates with these domain skills loaded:

  • debugging-patterns — root cause methodology, hypothesis testing
  • change-classification — change context awareness

Phase 1: EXPLORE

Gather all evidence before theorizing. Execute in parallel:

# Output: `###`-headed sections + KEY=value per
# `references/command-output-format.md`.

echo "### Recent History"
# Capture into a var so an empty result emits an explicit STATE=empty
# sentinel rather than a silent heading.
RECENT_LOG=$(git log --oneline -10 2>/dev/null)
if [ -z "$RECENT_LOG" ]; then
  echo "STATE=empty"
else
  printf '%s\n' "$RECENT_LOG" | sed 's/^/COMMIT=/'
fi

echo ""
echo "### Recent Diff (last 3 commits)"
RECENT_DIFF=$(git diff HEAD~3..HEAD --stat 2>/dev/null)
if [ -z "$RECENT_DIFF" ]; then
  echo "STATE=empty"
else
  # Prefix raw stat lines with DIFF_STAT= per command-output-format.md.
  printf '%s\n' "$RECENT_DIFF" | sed 's/^/DIFF_STAT=/'
fi

echo ""
echo "### Current State"
echo "BRANCH=$(git branch --show-current 2>/dev/null)"
UNCOMMITTED_COUNT=$(git status --porcelain 2>/dev/null | wc -l | tr -d ' ')
echo "UNCOMMITTED_COUNT=$UNCOMMITTED_COUNT"
[ "$UNCOMMITTED_COUNT" != "0" ] && git status --short 2>/dev/null | head -20 | sed 's/^/UNCOMMITTED_LINE=/'

true

FlowRun (v3 runtime)

/flow:debug is a long-running workflow, so it gets a durable FlowRun. The companion FlowGoal is created later (after hypothesis confirmation), so the run forward-references its id. Runs are gated by flow.runtime.enabled (default true); v2 projects that opted out see FLOW_RUN_STATE=skip and the wiring is a no-op.

# FLOW_RUN_BLOCK_BEGIN
CASCADE="$(__fr="${CLAUDE_PLUGIN_ROOT:-}";[ -x "$__fr/bin/cascade-resolve.sh" ]||__fr=$({ echo plugins/flow;ls -d "$HOME"/.claude/plugins/cache/synapti-marketplace/flow/*/ 2>/dev/null|sort -Vr;echo "$HOME/.claude/plugins/marketplaces/synapti-marketplace/plugins/flow"; }|while read -r __p;do [ -x "${__p%/}/bin/cascade-resolve.sh" ]&&{ echo "${__p%/}";break;};done);echo "$__fr")/bin/cascade-resolve.sh"
if [ ! -x "$CASCADE" ]; then
  echo "FLOW_RUN_STATE=blocked"
  echo "FLOW_RUN_ERROR=cascade-resolve.sh missing or non-executable at $CASCADE"
  true; exit 0
fi
RUNTIME_ENABLED=$("$CASCADE" --default "true" '.flow.runtime.enabled' 2>/dev/null)
if [ "$RUNTIME_ENABLED" != "true" ]; then
  echo "FLOW_RUN_STATE=skip"
  echo "FLOW_RUN_REASON=flow.runtime.enabled is not true (v2 mode)"
else
  RUN_ID="$(date -u +%Y-%m-%dT%H%M%SZ)-debug"
  # The goal id must match the FlowGoal metadata.id pattern
  # ^[a-z0-9][a-z0-9-]{0,63}$ — no uppercase, so it cannot reuse the ISO run
  # timestamp (which carries T/Z). Use a hyphen-only lowercase stamp.
  GOAL_TS="$(date -u +%Y-%m-%d-%H%M%S)"
  echo "FLOW_RUN_STATE=create"
  echo "RUN_ID=$RUN_ID"
  echo "WORKFLOW=debug"
  echo "INITIAL_PHASE=preflight"
  echo "GOAL_LINK=debug-${GOAL_TS}"
fi
# FLOW_RUN_BLOCK_END
true

Read the full file on GitHub · 207 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. yesterday First seen · 207 lines · 20 tokens per session scan A bbf985a32b6c

Subscribe to this mod's changes

debug is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 2,367 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.