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/huangruiteng/loopx/loopx-benchmarknpx skills add huangruiteng/loopx --skill loopx-benchmarkgit clone --depth 1 https://github.com/huangruiteng/loopxWhat 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 | $0.00069 | $0.01724 |
| Opus 5 | $0.00034 | $0.00862 |
| Sonnet 5 | $0.00014 | $0.00345 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
loopx-benchmark 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 yesterday.
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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LoopX Benchmark Workflow
Use this skill for a LoopX-managed benchmark experiment. The builtin
benchmark-toolkit capability owns provider-neutral experiment state and
integrity boundaries. This packaged skill is its task-triggered Agent playbook.
The capability is catalog-ready without a per-Goal enable switch. Installing this skill does not grant runner, shell, network, credential, private-evidence, or Goal mutation authority. Respect the selected todo's required capabilities, any external provider binding, host permissions, and user gates.
Capability surface
loopx capability show benchmark-toolkit --format json— catalog entry with usage hints, role boundaries, and the post-run case-insight template.loopx benchmark --help— subcommands (experiment-board-show, experiment-board-upsert, source-revision-fence, integrity-qualification, classify-artifacts).
Select the operating lane
- Inspect or explain: use
capability showandbenchmark --help; remain read-only. Do not create an experiment-board row merely because the user asks what the toolkit does. - Plan, select, or launch a run: follow the experiment sequence below. The first action is to read the board; a launch still requires an authorized runner and admitted source.
- Monitor an active campaign: read the board and runtime-owned projections; update only on material run transitions. Do not manufacture progress from a timer tick.
- Analyze a terminal run: wait until solving is terminal and scoring is complete before reading hidden evaluator evidence or writing a case insight.
For a generic library microbenchmark or an eval with no LoopX Goal/board, use the task's normal tools instead of imposing this workflow.
Experiment sequence
- Read the experiment board before launching or selecting a case.
Inspect baseline, treatment, explore, countability, effort, and insight rows before choosing the next arm.loopx benchmark experiment-board-show --goal-id <GOAL_ID> --format json
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.
- yesterday First seen · 149 lines · 69 tokens per session scan A a158afdbad3f
loopx-benchmark is a skill published in the GitHub repository huangruiteng/loopx (5,313 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 1,724 once invoked, about $0.0003 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
smart-contract-audit
Comprehensive smart contract security audit framework with multi-expert analysis. Use for full audits of Ethereum / EVM Solidity and Vyper, Solana / SVM Anchor Rust, TON / FunC / Tact, or Sui / Move projects.
jwt-attacks
Forge and re-sign captured JWTs to test signature validation - algorithm confusion (alg:none, RS256 to HS256), key injection, and secret cracking. Use when testing JWT or bearer-token auth.
infrastructure-audit
Comprehensive infrastructure security audit framework for IaC, Docker, Kubernetes, and cloud configurations. Use for full infrastructure audits.
external-enumeration
Passively map a company's domains, subdomains, DNS ownership, tech stack, and CDNs. Use to recon an external attack surface or enumerate subdomains.
broken-access-control
Replay captured requests with swapped identities and bumped object IDs to surface broken access control. Use when testing for IDOR or authz flaws.
http-request-smuggling
Detect HTTP request smuggling by desynchronising front-end and back-end request parsing, using raw-socket timing and differential probes. Use when testing for HTTP desync (CL.TE, TE.CL).