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/bezhai/chiwei-platform/api-testnpx skills add bezhai/chiwei-platform --skill api-testgit clone --depth 1 https://github.com/bezhai/chiwei-platformWhat 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 | $0.00951 |
| Opus 5 | $0.00034 | $0.00476 |
| Sonnet 5 | $0.00014 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
api-test scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: 项目 HTTP API 调用 helper。写路径就行,scripts/http.sh 自动补 $PAAS_API、注 PAAS_TOKEN、透泳道,统一返回 {status, ms, body}。需要复杂 curl 能力(stream、文件、TLS/proxy、详细调试)时直接 curl,并说明原因。 What it actually says
/api-test
scripts/http.sh 比裸 curl 强的地方:你只写路径,剩下的它办。
- 以
/开头的路径自动拼上$PAAS_API;完整http(s)://URL 原样使用。 - 路径在
/dashboard/...或/api/paas/...下时,自动注入X-API-Key: $PAAS_TOKEN。对内对外一把钥匙——dashboard 也认 PAAS_TOKEN,两个面同一个 token,调用方不用再想该传哪个。 --lane LANE自动加x-lane头;显式传了X-API-Key/x-lane或--no-auth时不覆盖。- 始终返回
{"status":..,"ms":..,"body":..},ms是耗时。
完整 http(s):// URL 永远不自动注 token,所以历史上"传完整 URL + 显式 header"的调用方不受影响。
这个 helper 不替代 curl。它不支持的场景直接用 curl,不要让用户手动代劳:stream、文件上传/下载、长日志、复杂 TLS/proxy/redirect、-v 看握手。
用法
HTTP=.claude/skills/api-test/scripts/http.sh
# 裸路径:自动补 base + 自动注 PAAS_TOKEN
$HTTP GET /dashboard/api/ops/services
$HTTP GET "/api/paas/apps/agent-service/resolved-config?lane=prod"
# 带泳道
$HTTP --lane ppe-foo GET /api/paas/apps/agent-service/pods
# POST(第三个参数是 JSON body)
$HTTP POST /api/paas/apps/x '{"a":1}'
# 选项放任意位置都认(含末尾)
$HTTP GET /dashboard/api/ops/services --jq '.apps | length'
# 断言状态码:不匹配则退出码非 0(脚本里好用)
$HTTP --expect 200 GET /dashboard/api/health
# 其它选项:--timeout SEC(默认 60)、--save FILE、--no-auth、--raw
$HTTP --timeout 180 GET /dashboard/api/...
$HTTP PUT /api/paas/apps/x @/tmp/body.json
$HTTP POST /api/paas/... --data "plain text" "Content-Type: text/plain"
# 需要原生 curl 能力时显式透传
$HTTP --curl -v --max-time 300 -H "X-API-Key: $PAAS_TOKEN" "<url>"
选项
--lane LANE加x-lane(也可用HTTP_LANE环境变量)--jq FILTER对原始 body(不是{status,ms,body}外层)跑jq -r,只打印结果--expect CODE状态码 ≠ CODE 时退出码非 0--save FILE额外把原始 body 落盘--no-auth不自动注 token;--raw直出原始 body(不包 JSON、不计时)--curl <args...>后续参数原样交给 curl
输出
{"status": 200, "ms": 36, "body": {"key": "value"}}
{"status": 500, "ms": 12, "body": {"message": "error detail"}}
{"status": 0, "error": "curl exit 28: timeout"}
测试
scripts/test_http.sh:dry-run 单测(解析/补 base/注 token/透泳道)+ 本地 server e2e(计时/--jq/--expect)。改 http.sh 后跑 bash .claude/skills/api-test/scripts/test_http.sh。
What ships with it
2 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.
- 2d ago First seen · 70 lines · 69 tokens per session scan A dfd245a0fdac
api-test is a skill published in the GitHub repository bezhai/chiwei-platform (20 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 951 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (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…