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 skills/understudylabs/understudy-agent-tools/export-tracenpx skills add understudylabs/understudy-agent-tools --skill export-tracegit clone --depth 1 https://github.com/understudylabs/understudy-agent-toolsWhat 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 | $0.00071 | $0.00935 |
| Opus 5 | $0.00036 | $0.00467 |
| Sonnet 5 | $0.00014 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
export-trace 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 2d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Export Trace
Retrieve one explicit hosted trace without scanning the capture catalog. Resolve its request IDs through the customer trace lookup endpoint, then reuse the bounded request capture exporter.
Safety Gates
- Treat a bare
trace_idas authorization for a redacted local summary export, not for raw prompts or completions. - Use
--include-payload --yesonly when the developer explicitly asks for the full, raw, or complete trace/captures. Announce that the files may contain prompts, completions, and tool payloads before running it. - Keep outputs under
.understudy/; never print, paste, commit, or upload trace bodies. - Never ask for API keys in chat. Use existing Understudy credentials and report only auth presence or errors.
- Never replace the trace lookup with project-wide capture pagination. If the lookup endpoint is unavailable, stop and report the backend dependency.
Resolve CLI
Prefer the installed understudy binary. In this repository checkout:
npm run build
node dist/bin.js status --json
Use node dist/bin.js in place of understudy below when necessary.
Flow
-
Resolve the project from repo config or an explicit
--project/--project-id. Resolve--workloadonly when the developer supplied or requested that narrower scope. -
For redacted metadata, run:
understudy traces export <trace-id> \ --project <project> \ --out .understudy/traces/<trace-id> -
For an explicitly requested full trace, run:
understudy traces export <trace-id> \ --project <project> \ --out .understudy/traces/<trace-id> \ --include-payload --yesFor several explicit IDs, put one per line in a private local file and use
--trace-ids-file <path>. Do not use or recreate an unbounded--alloperation. -
Inspect only metadata artifacts:
trace.json—trace_id, orderedrequest_ids, and export counts;failed-request-ids.txt— request captures to retry;failed-trace-ids.txt— trace lookups or trace exports to retry;*.summary.jsonor*.payload.json— private per-request files.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 101 lines · 71 tokens per session scan A 1a6804d30f12
export-trace is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 935 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…