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 cubeplexai/cubepi --skill cubepi-tracegit clone --depth 1 https://github.com/cubeplexai/cubepiWrote 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/cubeplexai/cubepi/cubepi-trace)<a href="https://agentmods.dev/skills/cubeplexai/cubepi/cubepi-trace"><img src="https://agentmods.dev/badge/skills/cubeplexai/cubepi/cubepi-trace/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/cubeplexai/cubepi/cubepi-trace"><img src="https://agentmods.dev/badge/skills/cubeplexai/cubepi/cubepi-trace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 187 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00129 | $0.03281 |
| Opus 5 | $0.00064 | $0.01640 |
| Sonnet 5 | $0.00026 | $0.00656 |
| Haiku 4.5 | $0.00013 | $0.00328 |
Grade A, and why
cubepi-trace scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# Shell-executable curl (uses $BASE_URL / $API_KEY env vars) How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging cubepi runs with cubepi trace
cubepi can record every agent run as an OpenTelemetry span tree, written to
local JSONL files. The cubepi trace CLI reads those files so you can see
exactly what happened inside a run without re-running it: which LLM calls and
tool calls fired, in what order, what each returned, where it errored, and the
token/cache counts. Reach for this before guessing at a bug.
When this applies
- The final answer is missing, truncated, or the run "ended" with no reply.
- A tool (web_search, web_fetch, execute, MCP tool, …) returned something wrong or empty, or the agent looped.
- The model returned a 4xx/5xx (e.g.
BadRequestError), or the run status iserror. - Token / cache / cost numbers look wrong.
- You just need to understand the agent's actual trajectory for a given input.
- A background LLM call (e.g. memory consolidation via
Tracer.oneshot()) isn't behaving as expected — oneshot calls produceinvoke_agentspans too and are searchable by metadata.
Prerequisites (one-time)
Tracing must be on and recording content for the run you want to inspect. In cubebox it's config-driven (dynaconf):
tracing.enabled: truetracing.directory: ./cubepi-traces(default; relative to the backend cwd)tracing.record_content: true(needed to see prompts / tool args / results; off = you get the span tree and timings but no content)
Env override form: CUBEBOX_TRACING__ENABLED=true,
CUBEBOX_TRACING__RECORD_CONTENT=true, CUBEBOX_TRACING__DIRECTORY=....
cubebox's config.development already enables this. Files land at
<directory>/<YYYY-MM-DD>/<trace_id>.jsonl — sharded by trace_id, so one
file holds the whole trace, including any nested subagent runs (they inherit
the parent's trace). A trace that crosses UTC midnight is split across two date
dirs; the CLI merges them. (cubepi.run_id is still recorded as a per-span
attribute if you need to distinguish individual runs within a trace.)
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.
- 11d ago First seen · 271 lines · 129 tokens per session scan A a76c7ec643c0
cubepi-trace is a skill published in the GitHub repository cubeplexai/cubepi (54 stars, last pushed 5d ago), licensed MIT. It adds 129 tokens to every session and 3,281 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
code-review
This skill should be used when the user asks for a code review of a change — a pull request, merge request, branch, commit range, working-tree change, or pasted diff — covering correctness, security, performance, structure, and repository-specific rules. Trigger on phrases like "review this PR", "review this MR"…
plan
This skill should be used when the user asks to explore a codebase and design implementation plans without making any changes. Trigger when users say 'plan how to implement X', 'design an approach for Y', 'explore the codebase before changing Z', 'create an implementation strategy', 'analyze how to refactor X', 'map…
security-audit
This skill should be used when the user asks to review code for security vulnerabilities, audit a pull request or merge request for risks, check if code is safe, find injection flaws or hardcoded secrets, or assess the security posture of a feature or codebase area. Use this skill even when the user doesn't say…
init
This skill should be used when a user asks to initialize a repository for AI agents, create or update an AGENTS.md file, scaffold agent instructions for a codebase, or improve existing agent guidance. Triggers include phrases like 'create an AGENTS.md', 'set up agent instructions', 'initialize this repo for coding…
skill-creator
Guide for creating effective skills that extend DAIV agent with specialized knowledge, workflows, or tool integrations. Use this skill when the user wants to create a new skill, update an existing skill, or get guidance on skill design patterns.
hermes-s6-container-supervision
Modify or debug s6 services in the Hermes Docker image.