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 trapstreet/trapstreet-skills --skill trapstreet-setupgit clone --depth 1 https://github.com/trapstreet/trapstreet-skillsWrote 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/trapstreet/trapstreet-skills/trapstreet-setup)<a href="https://agentmods.dev/skills/trapstreet/trapstreet-skills/trapstreet-setup"><img src="https://agentmods.dev/badge/skills/trapstreet/trapstreet-skills/trapstreet-setup/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/trapstreet/trapstreet-skills/trapstreet-setup"><img src="https://agentmods.dev/badge/skills/trapstreet/trapstreet-skills/trapstreet-setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00083 | $0.01039 |
| Opus 5 | $0.00042 | $0.00519 |
| Sonnet 5 | $0.00017 | $0.00208 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade C, and why
trapstreet-setup 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 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.
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 -LsSf https://astral.sh/uv/install.sh | sh # macOS/Linux, official script Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh # macOS/Linux, official script How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trapstreet-setup -- install and authorize
Target state: tp runs, and (only if the user wants to submit) tp auth status --verify shows
the correct identity. Verify each step before moving to the next.
Say this first, to lower the stakes: local scoring (tp run) needs no authorization and no
GitHub account -- once tp is installed, trapstreet-solution-scaffold (or
trapstreet-task-scaffold) can already build and run against a task. Authorization (Step 4) is
only needed to submit to the leaderboard.
Step 1 -- check current state (installation may not be needed at all)
which uv && uv --version
which tp && tp --help | head -5 # do NOT verify with `tp --version` -- old versions lack that
# flag and throw a scary Error while the tool is actually fine
uv tool list | grep -i trap # real installed package name: current is trap-cli;
# an older machine may instead have trapstreet-cli
tp auth status --no-verify 2>&1 | head -5
All good already? Don't reinstall -- report the current state (tool works, login status) and
move straight to whatever the user actually wants to do. If the installed package is
trapstreet-cli (not trap-cli), recommend upgrading: uv tool uninstall trapstreet-cli && uv tool install trap-cli -- the old package predates the trap.yaml schema that
trapstreet-solution-scaffold's templates target, and has no confirmation gates for remote code
/ unanchored runs. If the user declines, say so plainly rather than pretending it's current.
Step 2 -- install uv (if missing)
curl -LsSf https://astral.sh/uv/install.sh | sh # macOS/Linux, official script
# or: brew install uv
uv --version # verify; if not found, reopen the shell or source the profile
Step 3 -- install tp
uv tool install trap-cli
tp --help | head -5
The command is tp; the package is trap-cli. If Step 1 detected the old trapstreet-cli
package instead, uv tool upgrade trap-cli against it returns "not installed" (wrong package
name) -- uninstall the old one and install the new one, don't try to upgrade in place.
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 · 87 lines · 83 tokens per session scan C 7e1466335643
trapstreet-setup is a skill published in the GitHub repository trapstreet/trapstreet-skills (5 stars, last pushed 15d ago), licensed MIT. It adds 83 tokens to every session and 1,039 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 2026-08-31.
Other skills, from other repositories
iris-eval
Evaluate AI agent output quality, safety, and cost using the Iris MCP server. Use when building, testing, or shipping agents and the user wants to score output quality, detect PII or prompt injection, verify citations, track cost per query, enforce cost budgets, add tracing/observability to an agent, or set up…
agent-evaluation-v2
Agent Evaluation workflow skill. Use this skill when the user needs Testing and benchmarking LLM agents including behavioral testing, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
agent-evaluation
Agent Evaluation workflow skill. Use this skill when the user needs Testing and benchmarking LLM agents including behavioral testing, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
agent-evaluation-v3
Agent Evaluation workflow skill. Use this skill when the user needs Testing and benchmarking LLM agents including behavioral testing, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
duckduckgo-search
Free keyless web, news, and image search via ddgs.