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 skills add Waddling-Penguin/mogkit --skill spec-stress-testgit clone --depth 1 https://github.com/Waddling-Penguin/mogkitWrote 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/waddling-penguin/mogkit/spec-stress-test)<a href="https://agentmods.dev/skills/waddling-penguin/mogkit/spec-stress-test"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/spec-stress-test/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/waddling-penguin/mogkit/spec-stress-test"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/spec-stress-test.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00004 | $0.01110 |
| Opus 5 | $0.00002 | $0.00555 |
| Sonnet 5 | $0.00001 | $0.00222 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
spec-stress-test 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 10d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
A spec read by its author looks airtight. The author has the mental model the words gesture at, so gaps and ambiguities slide past unnoticed. This skill reads the spec as an adversary — looking for what it does not say, where two requirements collide, and where the user will be stranded when reality deviates from the happy path.
It does NOT rewrite the spec. It does not suggest replacement language. It does not produce a "v2 with my fixes." The output is the attack list. The PM decides which attacks deserve a fix and writes the fixes themselves. Rewriting the spec would let the PM skip the work of deciding which problems are real, which are out of scope, and which are acceptable risks.
Procedure
- Read the pasted spec end to end.
- Identify the implicit happy path the spec assumes. Note it briefly — it is the contrast against which everything else gets examined.
- Generate attacks in five categories. For each attack, write one line, in the user's perspective where possible: a. Edge cases — inputs, states, or scales the spec doesn't address (empty state, max state, single-user, ten-million-user, offline, slow network, the third device). b. Failure modes — what breaks when a dependency is unavailable, partial, slow, or wrong. What does the user see? c. Race conditions / requirement collisions — two requirements in the spec that contradict each other, or that work individually but not when both fire at once. d. Unstated assumptions — beliefs the spec relies on without naming. ("Assumes the user has already done X." "Assumes the data is clean.") e. User-visible failure UX — for each failure mode, what does the end-user actually experience? Silent failure, confusing state, lost work, etc.
- Rank every attack by severity. Use three levels:
- Critical — ships broken or unsafe; users lose data, get stuck, or are misled.
- High — degrades the experience meaningfully for a non-trivial segment.
- Medium — real but narrow; acceptable to defer with a stated mitigation. Do not pad with low-severity items. If something does not clear "Medium", drop it.
- Add a short What the spec doesn't tell me section listing the information you'd need from the PM to sharpen any "unclear" findings above. This is the gap the spec itself has, not your gap.
- Emit the output contract. Do not propose replacement spec language.
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.
- 10d ago First seen · 101 lines · 4 tokens per session scan A 360ec46e0593
spec-stress-test is a skill published in the GitHub repository Waddling-Penguin/mogkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 4 tokens to every session and 1,110 once invoked, about $0.0000 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 2026-08-31.
Other skills, from other repositories
find-skills
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.