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/capture-evidencenpx skills add understudylabs/understudy-agent-tools --skill capture-evidencegit clone --depth 1 https://github.com/understudylabs/understudy-agent-toolsWrote 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/understudylabs/understudy-agent-tools/capture-evidence)<a href="https://agentmods.dev/skills/understudylabs/understudy-agent-tools/capture-evidence"><img src="https://agentmods.dev/badge/skills/understudylabs/understudy-agent-tools/capture-evidence.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 | $0.00086 | $0.02895 |
| Opus 5 | $0.00043 | $0.01448 |
| Sonnet 5 | $0.00017 | $0.00579 |
| Haiku 4.5 | $0.00009 | $0.00290 |
Grade A, and why
capture-evidence 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 3d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture Evidence
Use this worker when the developer has not yet produced current local evidence for the workload, or when any core artifact is missing, stale, ambiguous, or untrusted.
The OSS loop does not require registration, auth, provider keys, an Understudy account, or hosted gateway access. Do a sufficient local pass that turns the workload into auditable artifacts and can answer the named decision.
When the developer names a workload already captured by Understudy and the
active credentials can read it, use the hosted-workload front door in
references/hosted-workload-eval.md.
It freezes the exact source cohort, downloads payloads with approval, and runs
the same local trace foundry. A hosted eval workspace is not required to author
the verifier.
Safety Gates
Default to the evidence plan most likely to resolve the decision under the
developer's constraints, not the cheapest or smallest pass. Make cost, time,
scope, and expected confidence visible; use
../understudy/reference.md → Outcome-first spend
posture. A developer action that launches a named bounded evidence plan
authorizes its declared uploads, hosted calls, model evaluation, receipts, and
cleanup. Ask again only if the plan expands its displayed envelope.
Follow the repo public boundary in
../../docs/privacy-and-data-boundaries.md.
Prefer metadata, paths, hashes, counts, schemas, and representative examples.
Dropped workload content is available to the active analyst, and workload data
may move through the destination named by an activated plan. Never print,
commit, or transmit secrets; do not send data beyond the activated destination.
Goal
Create or refresh these artifacts under .understudy/capture-evidence/:
workload-profile.md
harness.json
environment.json
metric.json
splits.json
baseline.json
Each artifact must include a creation timestamp, source refs or path refs, and enough provenance for another agent to repeat the step without guessing.
What ships with it
4 files 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.
- 3d ago First seen · 234 lines · 86 tokens per session scan A ecc667d29a9e
capture-evidence is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 2,895 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…