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/synaptiai/synapti-marketplace/debuggit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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.
[](https://agentmods.dev/commands/synaptiai/synapti-marketplace/debug)<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>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.
| Model | Per session | Once 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 |
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.
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: $ARGUMENTS
Structured debugging with root cause analysis. Follows Explore > Plan > Code > Verify loop.
Required Skills
This command operates with these domain skills loaded:
debugging-patterns— root cause methodology, hypothesis testingchange-classification— change context awareness
Phase 1: EXPLORE
Gather all evidence before theorizing. Execute in parallel:
# Output: `###`-headed sections + KEY=value per
# `references/command-output-format.md`.
echo "### Recent History"
# Capture into a var so an empty result emits an explicit STATE=empty
# sentinel rather than a silent heading.
RECENT_LOG=$(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
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.
- yesterday First seen · 207 lines · 20 tokens per session scan A bbf985a32b6c
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.
Other commands, from other repositories
create-worktree
Follow these steps to create a git worktree.
hf.audit-tests
Run a comprehensive test quality audit across the entire repo. Analyzes test naming, structure, hygiene, factory usage, fluent builder patterns, anti-patterns, coverage gaps, and flaky patterns. Creates GitHub issues for findings so HydraFlow can process them.
hf.issue
Take a rough description from the user, research the relevant codebase, and create a well-structured GitHub issue with full context, file references, and acceptance criteria.
hf.memory
Scan the current conversation for architectural decisions, bug root causes, configuration choices, codebase patterns, and workflow preferences. Write each as a memory item to the local JSONL store for ingestion by the memory sync worker.
paper-trail-review
Review and arbitrate problematic references (cascade-exhausted, unresolved UID, awaiting OCR). Generates an up-to-date report, walks through cases by category, and applies arbitration decisions to the registry.
paper-trail-decide
Inspect a single reference in detail (identity, PDF status, acquisition history with verdicts, citation context in vault, state transitions) and decide its fate. Offers actionable decisions based on the ref's current state.