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 skills add axiomhq/cli --skill find-tracesgit clone --depth 1 https://github.com/axiomhq/cliWrote 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/skills/axiomhq/cli/find-traces)<a href="https://agentmods.dev/skills/axiomhq/cli/find-traces"><img src="https://agentmods.dev/badge/skills/axiomhq/cli/find-traces/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/axiomhq/cli/find-traces"><img src="https://agentmods.dev/badge/skills/axiomhq/cli/find-traces.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00037 | $0.01611 |
| Opus 5.5 | $0.00015 | $0.00644 |
| Sonnet 5.5 | $0.00007 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
find-traces 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 1mo 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.
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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trace Analysis
Analyze OpenTelemetry distributed traces to identify errors, latency issues, and root causes.
Arguments
When invoked with a trace ID (e.g., /find-traces abc123...), it's available as $ARGUMENTS.
Trace Dataset Discovery
First, find trace datasets:
axiom dataset list -f json
Look for datasets containing trace data (often named *traces*, *spans*, or otel-*).
Schema Discovery
Always verify field names first:
axiom query "['<trace-dataset>'] | getschema" --start-time -1h
Common Operations
Get Trace by ID
axiom query "['<dataset>']
| where trace_id == '<TRACE_ID>'
| sort by _time asc
| limit 100" --start-time -1h -f json
Find Error Traces
axiom query "['<dataset>']
| where _time >= ago(1h)
| where error == true
| extend error = coalesce(ensure_field(\"error\", typeof(bool)), false)
| summarize
start_time = min(_time),
total_duration = max(duration),
span_count = count(),
error_count = countif(error),
services = make_set(['service.name']),
root_operation = arg_min(_time, name)
by trace_id
| sort by start_time desc
| limit 20" --start-time -1h -f json
Find Slow Traces
axiom query "['<dataset>']
| where _time >= ago(1h)
| where duration >= 1000000000
| summarize
start_time = min(_time),
total_duration = max(duration),
span_count = count(),
services = make_set(['service.name'])
by trace_id
| sort by total_duration desc
| limit 20" --start-time -1h -f json
Find Traces by Service
axiom query "['<dataset>']
| where _time >= ago(1h)
| where ['service.name'] == '<SERVICE>'
| summarize
start_time = min(_time),
total_duration = max(duration),
span_count = count(),
error_count = countif(error == true)
by trace_id
| sort by start_time desc
| limit 20" --start-time -1h -f json
Error Spans in Trace
axiom query "['<dataset>']
| where trace_id == '<TRACE_ID>'
| where error == true
| project _time, ['service.name'], name, duration, ['status.message']" --start-time -1h -f 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.
- 1mo ago First seen · 225 lines · 37 tokens per session scan A 97e98e83b880
find-traces is a skill published in the GitHub repository axiomhq/cli (60 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 1,611 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
tui-render-debug
Diagnose and fix pi-go TUI rendering corruption, especially displaced panels, stale rows, cursor drift, and terminal-specific ANSI incompatibilities.
golang-lint
Linting best practices and golangci-lint configuration for Golang projects — running linters, configuring .golangci.yml, suppressing warnings with nolint directives, interpreting lint output, and selecting linters. Use when configuring golangci-lint, asking about lint warnings or nolint suppressions, setting up code…
golang-troubleshooting
Troubleshoot Golang programs systematically - find and fix the root cause. Use when encountering bugs, crashes, deadlocks, or unexpected behavior in Go code. Covers debugging methodology, common Go pitfalls, test-driven debugging, pprof setup and capture, Delve debugger, race detection, GODEBUG tracing, and production…
golang-samber-oops
Structured error handling in Golang with samber/oops — error builders, stack traces, error codes, error context, error wrapping, error attributes, user-facing vs developer messages, panic recovery, and logger integration. Apply when using or adopting samber/oops, or when the codebase already imports…