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/me2resh/apexyard/challengenpx skills add me2resh/apexyard --skill challengegit clone --depth 1 https://github.com/me2resh/apexyardWrote 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/me2resh/apexyard/challenge)<a href="https://agentmods.dev/skills/me2resh/apexyard/challenge"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/challenge.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 | $0.00044 | $0.01133 |
| Opus 5 | $0.00022 | $0.00566 |
| Sonnet 5 | $0.00009 | $0.00227 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
challenge 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 5d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/challenge — Stress-test the premise with The Contrarian
/challenge <target> spawns the Contrarian agent (Naqid) to adversarially challenge an idea before you commit build effort to it. It is the premise-level analog of /code-review (Rex), /security-review (Hakim), and /design-review (Tariq) — but where those review built artifacts and gate a merge, the Contrarian challenges whether the idea is right at all and is advisory-only: it never writes a marker, never blocks a gate. The call stays yours.
This is the operational tool for the "play devil's advocate" reflex — made a first-class, repeatable move instead of an ad-hoc prompt.
When to use it
- Before writing a spec or filing an epic — pressure-test the idea while it's cheap to change.
- Before a big technical decision (
/decide) — surface the assumptions and the cheaper alternative. - Before committing to a multi-step plan — find the load-bearing assumption that, if wrong, sinks the plan.
- Any time you catch yourself agreeing with an idea too easily — that's exactly when an adversary earns its keep.
Usage
/challenge add a second database to handle reporting load
/challenge #345
/challenge projects/apexbrain/prd.md
/challenge the plan
The argument is free-form. Step 1 normalises it into a concrete target for the agent.
Process
1. Resolve the target
Classify the argument:
| Argument shape | Target the agent receives |
|---|---|
#N or owner/repo#N |
The ticket — instruct the agent to gh issue view <N> and challenge it. |
A path ending .md (or under projects/, docs/, prds/, designs/) that exists |
The document — the agent reads it and challenges it. |
the plan / this plan |
The most recent multi-step plan presented in the conversation — pass it inline to the agent. |
| Anything else (free text) | An idea stated in the conversation — pass the idea text (plus relevant conversation context) inline to the agent. |
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.
- 5d ago First seen · 79 lines · 44 tokens per session scan A de8d2d5a58f4
challenge is a skill published in the GitHub repository me2resh/apexyard (498 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,133 once invoked, about $0.0002 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
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…