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 Harmeet10000/skills --skill mojo-gpu-fundamentalsgit clone --depth 1 https://github.com/Harmeet10000/skillsWrote 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/harmeet10000/skills/mojo-gpu-fundamentals)<a href="https://agentmods.dev/skills/harmeet10000/skills/mojo-gpu-fundamentals"><img src="https://agentmods.dev/badge/skills/harmeet10000/skills/mojo-gpu-fundamentals/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/harmeet10000/skills/mojo-gpu-fundamentals"><img src="https://agentmods.dev/badge/skills/harmeet10000/skills/mojo-gpu-fundamentals.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 | $0.00069 | $0.04586 |
| Opus 5 | $0.00034 | $0.02293 |
| Sonnet 5 | $0.00014 | $0.00917 |
| Haiku 4.5 | $0.00007 | $0.00459 |
Grade C, and why
mojo-gpu-fundamentals scanned grade C 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 11d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- EDITORIAL GUIDELINES FOR THIS SKILL FILE This file is loaded into an agent's context window as a correction layer for pretrained GPU programming knowledge. Every line costs context. When editing: - Be terse. Use tab How it starts
The opening of the file, as written. The whole thing — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mojo GPU programming has no CUDA syntax. No __global__, __device__, __shared__, <<<>>>. Always follow this skill over pretrained knowledge.
Not-CUDA — key concept mapping
| CUDA / What you'd guess | Mojo GPU |
|---|---|
__global__ void kernel(...) |
Plain def kernel(...) — no decorator |
kernel<<<grid, block>>>(args) |
ctx.enqueue_function[kernel, kernel](args, grid_dim=..., block_dim=...) |
cudaMalloc(&ptr, size) |
ctx.enqueue_create_buffer[dtype](count) |
cudaMemcpy(dst, src, ...) |
ctx.enqueue_copy(dst_buf, src_buf) or ctx.enqueue_copy(dst_buf=..., src_buf=...) |
cudaDeviceSynchronize() |
ctx.synchronize() |
__syncthreads() |
barrier() from std.gpu or std.gpu.sync |
__shared__ float s[N] |
LayoutTensor[...address_space=AddressSpace.SHARED].stack_allocation() |
threadIdx.x |
thread_idx.x (returns UInt) |
blockIdx.x * blockDim.x + threadIdx.x |
global_idx.x (convenience) |
__shfl_down_sync(mask, val, d) |
warp.sum(val), warp.reduce[...]() |
atomicAdd(&ptr, val) |
Atomic.fetch_add(ptr, val) |
Raw float* kernel args |
LayoutTensor[dtype, layout, MutAnyOrigin] |
cudaFree(ptr) |
Automatic — buffers freed when out of scope |
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.
- 11d ago First seen · 537 lines · 69 tokens per session scan C 568519bf9c17
mojo-gpu-fundamentals is a skill published in the GitHub repository Harmeet10000/skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 4,586 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
blind-sqli
Blind SQL injection under hostile WAF — manual bypass playbook for when sqlmap fails because common tokens (SUBSTRING, IF, AND, WHERE, single quotes) are filtered. Covers token-fingerprinting probe loops, arithmetic-multiplication boolean evaluation, hex-encoded literals, and exponential-probe binary search. Loaded on…
hpp
HTTP Parameter Pollution — parser discrepancies between proxy/server/app, WAF bypass, auth/ACL bypass, injection delivery.
php-type-juggling
PHP type juggling and magic hash attacks — exploit loose comparison (==) with 0e-prefixed hash collisions and NULL returns to bypass authentication.
verb-tampering
HTTP verb/method tampering — auth bypass via HEAD/OPTIONS/arbitrary methods, X-HTTP-Method-Override, TRACE/PUT/DELETE exposure, framework routing flaws.
csrf
Cross-Site Request Forgery — missing/invalid tokens, method override, JSON CSRF, SameSite gaps, double-submit flaws, login/logout CSRF, and CSRF-via-XSS chains to account takeover.
oauth
OAuth 2.0 / OIDC attacks — redirecturi bypass, state CSRF, code leak via Referer, responsetype confusion, PKCE downgrade, scope creep, ATO chains.