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 tensormux/kernel-skills --skill debug-quantized-kernel-accuracygit clone --depth 1 https://github.com/tensormux/kernel-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/tensormux/kernel-skills/debug-quantized-kernel-accuracy)<a href="https://agentmods.dev/skills/tensormux/kernel-skills/debug-quantized-kernel-accuracy"><img src="https://agentmods.dev/badge/skills/tensormux/kernel-skills/debug-quantized-kernel-accuracy/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/tensormux/kernel-skills/debug-quantized-kernel-accuracy"><img src="https://agentmods.dev/badge/skills/tensormux/kernel-skills/debug-quantized-kernel-accuracy.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 | $0.00000 | $0.03146 |
| Opus 5.5 | $0.00000 | $0.01258 |
| Sonnet 5.5 | $0.00000 | $0.00629 |
| Haiku 4.5 | $0.00000 | $0.00315 |
Grade A, and why
debug-quantized-kernel-accuracy 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Debug Quantized Kernel Accuracy
Purpose
Guide the agent through a systematic process for diagnosing and isolating accuracy degradation in a quantized (INT8, FP8, or low-bit) kernel, from measuring the error to identifying the specific computational step responsible.
Use this when
- A quantized kernel produces outputs that differ from the fp32 reference by more than the expected quantization error bound.
- A model using quantized kernels shows accuracy degradation that exceeds what is expected for the chosen quantization scheme.
- A quantization refactor introduced a regression and the specific step that broke is not obvious.
- Debugging a quantized kernel that works correctly on some input shapes or batch sizes but fails on others.
Do not use this when
- The error is within the expected quantization error bound (approximately 0.5 * scale per element for well-calibrated INT8) and the downstream task accuracy loss is acceptable.
- The issue is clearly a non-accuracy bug (segfault, wrong shape, miscompilation) — fix the structural bug first.
- The degradation is due to model-level quantization sensitivity (certain layers or operators being inherently sensitive to quantization), which requires a quantization-aware training or mixed-precision approach rather than kernel debugging.
Inputs the agent should gather first
- The exact mathematical specification of what the quantized kernel is supposed to compute, written in terms of the original unquantized operation.
- The quantization scheme: per-tensor, per-channel, or per-token; symmetric or asymmetric; INT8, INT4, or FP8; signed or unsigned range.
- The scale computation method: offline calibration, per-batch dynamic quantization, or per-token dynamic quantization.
- The accumulation dtype: INT32, FP32, FP16, or FP8.
- The dequantization epilogue: where is scale applied, in what order, and what is the output dtype.
- A fp32 reference output for the same inputs (required for comparison).
- Whether the error is consistent across runs (deterministic) or varies (stochastic — possible race condition or non-deterministic reduction).
What ships with it
1 file 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.
- 1mo ago First seen · 127 lines · 0 tokens per session scan A 370353c9092b
debug-quantized-kernel-accuracy is a skill published in the GitHub repository tensormux/kernel-skills (82 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,146 tokens. 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
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
sglang-diffusion-benchmark-profile
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…
anti-entropy-governance
Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.