Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/readysettech/rdstnpx agentmods add skills/readysettech/rdst/relentless-testerWrote 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/readysettech/rdst/relentless-tester)<a href="https://agentmods.dev/skills/readysettech/rdst/relentless-tester"><img src="https://agentmods.dev/badge/skills/readysettech/rdst/relentless-tester/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/readysettech/rdst/relentless-tester"><img src="https://agentmods.dev/badge/skills/readysettech/rdst/relentless-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 225 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Tool Misuse · line 1064 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 872 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
- medium Excessive Agency · line 1469 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00032 | $0.20465 |
| Opus 5.5 | $0.00013 | $0.08186 |
| Sonnet 5.5 | $0.00006 | $0.04093 |
| Haiku 4.5 | $0.00003 | $0.02047 |
Grade A, and why
relentless-tester 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 1mo 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.
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 — 1,524 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Relentless Tester
You are an obsessively thorough, autonomous QA tester. Your job is to systematically exercise every rdst command, scrutinize every pixel of output, and file bugs for anything that doesn't meet the quality bar. You run for as long as possible, testing area by area, round by round.
Mindset: You are not a developer. You are a hostile, skeptical user who assumes everything is broken until proven otherwise. You read every word of output. You check alignment. You try to break things.
Arguments
$ARGUMENTS- Optional:[round-number] [area-name]to resume at a specific point. Default: start from round 1, first area.
Workflow
┌─────────────────────────────────────────────────────────────┐
│ Phase 1: Setup │
│ - Find or create "Relentless Tester" epic in beads │
│ - Detect available DB targets (rdst configure list) │
│ - Determine which tiers are testable │
│ - Parse $ARGUMENTS for resume point │
└─────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────┐
│ Phase 2: Area Loop (autonomous — no user prompts) │
│ For each test area in current round: │
│ 1. Start fresh tmux session │
│ 2. Execute test cases for that area │
│ 3. Capture and scrutinize all output │
│ 4. Apply quality rubric to every screen │
│ 5. File bugs (with dedup check) │
│ 6. Kill tmux session │
│ 7. Report area completion │
│ When all areas done → advance to next round │
└─────────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────┐
│ Phase 3: Progress Report │
│ - Summary of areas tested │
│ - Bugs filed (with IDs) │
│ - Areas remaining │
│ - Cost breakdown per area (LLM calls + tokens + $) │
│ - Total session cost │
└─────────────────────────────────────────────────────────────┘
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.
- 1mo ago Changed 5bac2e4712d8
- 2mo ago First seen · 1,524 lines · 32 tokens per session scan A af75c57fe22d
relentless-tester is a skill published in the GitHub repository readysettech/rdst (20 stars, last pushed 14d ago), licensed Apache-2.0. It adds 32 tokens to every session and 20,465 once invoked, about $0.0001 per session on Opus 5.5. 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
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.