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/install-agent-adapternpx skills add understudylabs/understudy-agent-tools --skill install-agent-adaptergit 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 | $0.00083 | $0.01127 |
| Opus 5 | $0.00042 | $0.00563 |
| Sonnet 5 | $0.00017 | $0.00225 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade C, and why
install-agent-adapter scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/UnderstudyLabs/understudy-agent-tools/main/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/UnderstudyLabs/understudy-agent-tools/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install the Understudy Agent Adapter
Understudy is agent-platform-neutral at the skill layer. The product is the
shared skills/ tree; Claude Code, Cursor, Codex, OpenCode, Hermes Agent, and
Devin only differ in how they discover and reload those skills.
Use this skill for setup, refresh, verification, uninstall, or "why can't my agent see Understudy?" requests. Keep the workflow local-first and pick the smallest adapter path that matches the developer's agent.
Choose Platform
If the developer named a platform, use it. Otherwise prefer the active agent surface you are running inside. If that is unclear, inspect available CLIs and local app state:
command -v claude || true
command -v cursor || true
command -v codex || true
command -v opencode || true
command -v hermes || true
test -n "$DEVIN" && echo devin-session
test -d "$HOME/.cursor" && echo cursor-config
test -d "$HOME/.config/opencode" && echo opencode-config
test -d "$HOME/.local/share/opencode" && echo opencode-data
test -d "$HOME/.hermes" && echo hermes-config
Platform details live in reference.md:
- Claude Code: local marketplace plugin, then user runs
/reload-plugins. - Cursor: symlink this repo into
~/.cursor/plugins/local/understudy, then reload the window. - Codex: register the local marketplace, then user installs/enables from
/plugins. - OpenCode: link the shared skills into
~/.config/opencode/skills, then restart or open a new TUI session. - Hermes Agent: register a stable
~/.understudy/skillssymlink inskills.external_dirs(~/.hermes/config.yaml), then run/reload-skills. - Devin: the public installer builds the GitHub source and links the CLI
globally; Devin reads
AGENTS.mdand accesses the sharedskills/tree directly from the cloned repo.
Procedure
For a full Understudy update, rerun the public installer first. It refreshes the managed GitHub checkout, rebuilds the CLI, and then reinstalls adapters:
curl -fsSL https://raw.githubusercontent.com/UnderstudyLabs/understudy-agent-tools/main/install.sh | bash
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.
- 3d ago First seen · 136 lines · 83 tokens per session scan C 5c85ea95e959
install-agent-adapter is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 4d ago), licensed MIT. It adds 83 tokens to every session and 1,127 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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
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…