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/nazarkalytiuk/tarn/tarn-api-testingnpx skills add NazarKalytiuk/tarn --skill tarn-api-testinggit clone --depth 1 https://github.com/NazarKalytiuk/tarnWrote 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/nazarkalytiuk/tarn/tarn-api-testing)<a href="https://agentmods.dev/skills/nazarkalytiuk/tarn/tarn-api-testing"><img src="https://agentmods.dev/badge/skills/nazarkalytiuk/tarn/tarn-api-testing.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 | $0.00106 | $0.09914 |
| Opus 5 | $0.00053 | $0.04957 |
| Sonnet 5 | $0.00021 | $0.01983 |
| Haiku 4.5 | $0.00011 | $0.00991 |
Grade C, and why
tarn-api-testing 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 4d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- **Code actions** — `extract env var` (lift a string literal into an inline `env:` key), `capture this field` (stub a `capture:` from a JSONPath literal under the cursor), `scaffold assert from response` (generate a pre Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Write, run, debug, and iterate on API tests using Tarn — a CLI-first API testing tool with .tarn.yaml files and structured JSON output. Use when: writing API tests, running tarn commands, debugging test failures, generat How it starts
The opening of the file, as written. The whole thing — 784 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tarn API Testing Skill
Tarn is a CLI-first API testing tool. Tests are declarative YAML files (.tarn.yaml). Results are structured JSON designed for AI agent consumption. Single binary, zero runtime dependencies.
Core Workflow — Failures-First Loop
This is the canonical sequence. Default to it for every debugging task. Do not reach for the full JSON report until steps 3–6 have failed to answer the question.
1. tarn validate <path> # syntax/config before running
2. tarn run <path> # produces .tarn/runs/<run_id>/
3. tarn failures # root-cause groups; cascades collapsed
4. tarn inspect last FILE::TEST::STEP # full context for ONE failure
5. Patch tests or application code
6. tarn rerun --failed # reruns only the failing subset
7. tarn diff prev last # confirm fixed / new / persistent
8. Full report.json only when 3–6 are insufficient
Agent rules (read before doing anything else)
- Never slurp
report.jsoniffailures.jsonis sufficient.failures.jsonis a 1–50 KB file with one entry per failing step.report.jsonis often megabytes.tarn failuresis the correct entry point, notcat .tarn/last-run.json | jq .... - Never parse the full run JSON when a summary + inspect will answer the question.
tarn inspect last FILE::TEST::STEPopens one step's request/response/assertion block directly. Use it instead of grepping the whole report. - Never blame business logic before confirming the response shape didn't drift. See the "Response-shape drift" section below — most
assertion_failed+skipped_due_to_failed_captureclusters are a single upstream capture path that no longer matches the new response body. - Cascade skips (
skipped_due_to_failed_capture) are suppressed noise. Fix the root cause first.tarn failuresalready collapses them into└─ cascades: N skipped. Do NOT open each cascade skip individually; they will all resolve when the upstream step is fixed. - Always
tarn validatebeforetarn run. Always use--format json(orllm) when parsing results programmatically.
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.
- 4d ago First seen · 784 lines · 106 tokens per session scan C a379bd72f459
tarn-api-testing is a skill published in the GitHub repository NazarKalytiuk/tarn (5 stars, last pushed 3mo ago), licensed MIT. It adds 106 tokens to every session and 9,914 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, 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
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…