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/talayash/spring-fleet/debuggit clone --depth 1 https://github.com/talayash/spring-fleetWhat 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 | $0.00045 | $0.00506 |
| Opus 5 | $0.00023 | $0.00253 |
| Sonnet 5 | $0.00009 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00051 |
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.
What it actually says
Debug a cross-service runtime issue in the Spring Boot fleet.
Input: $ARGUMENTS — one of:
- an OTel trace_id (32 lowercase hex chars) — preferred, modern path.
- a legacy sessionId / requestId — fallback for older fleets.
- a pasted error or stack trace — agent extracts a trace key from nearby log lines.
- a pasted screenshot of a Grafana / Tempo / Jaeger / Kibana panel or an IDE / terminal stack — the model reads it directly (Claude is multimodal); extract the trace_id or service + timestamp from the image and use that as the correlation handle.
Steps:
- Locate
spring-fleet.config.json(cwd, else ask the user / suggest/fleet-init). - Use the debugging-runtime-logs skill.
- If the input is an image: read it first. Look for a
trace_id/traceparentvalue, a sessionId, a service name + timestamp window, or an exception class + message. Use whichever you find as the correlation handle (prefer trace_id). Quote what you extracted so the user can sanity-check it. - Dispatch the log-correlator agent with the config path and the
resolved handle to build the cross-service timeline and isolate the failure
origin. Prefer the
correlate_by_traceMCP tool when available. - If the cause is cross-service, dispatch fleet-explorer to confirm the
call path and map the failing hop to
file:line. - Report: what happened, the timeline, failure origin (service +
file:line), how it surfaced upstream, the ROOT-CAUSE HYPOTHESIS block from the log-correlator (WHAT / WHERE / WHY / CONFIDENCE / SUGGESTED FIX), and any service missing a log file.
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 · 35 lines · 45 tokens per session scan A e83f80308e04
debug is a command published in the GitHub repository talayash/spring-fleet (2 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 506 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
index
Command "index" from MadaraUchiha-314/the-loop, covering commands, the control plane, daemon commands, repo-scoped commands and maintenance.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.