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 Ascend/agent-skills --skill ascend-transformer-boostgit clone --depth 1 https://github.com/Ascend/agent-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/ascend/agent-skills/ascend-transformer-boost)<a href="https://agentmods.dev/skills/ascend/agent-skills/ascend-transformer-boost"><img src="https://agentmods.dev/badge/skills/ascend/agent-skills/ascend-transformer-boost/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/ascend/agent-skills/ascend-transformer-boost"><img src="https://agentmods.dev/badge/skills/ascend/agent-skills/ascend-transformer-boost.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 | $0.00090 | $0.02372 |
| Opus 5 | $0.00045 | $0.01186 |
| Sonnet 5 | $0.00018 | $0.00474 |
| Haiku 4.5 | $0.00009 | $0.00237 |
Grade A, and why
ascend-transformer-boost 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.
The source is not reproduced here
Licensed MulanPSL-2.0
The repository is licensed MulanPSL-2.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
16 files 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.
- docs/agent-skills-background.md 7.2 KB
- docs/atb-skills-guide.md 20 KB
- rules/project-description.md 497 B
- skills/atb-aclnn-operator-migration/SKILL.md 8.9 KB
- skills/atb-aclnn-operator-replacement-designer/references/softmax_aclnn_runner_reference.md 9.7 KB
- skills/atb-aclnn-operator-replacement-designer/SKILL.md 16 KB
- skills/atb-aclnn-operator-replacement-designer/templates/design-template.md 5.5 KB
- skills/atb-csv-testcase-generator/SKILL.md 19 KB
- skills/atb-csv-tester/scripts/run-csv-tests.sh 10 KB runs code
- skills/atb-csv-tester/SKILL.md 13 KB
- skills/atb-csv-tester/tests/run-tests.sh 7.2 KB runs code
- skills/atb-debug-guide/SKILL.md 8.4 KB
- skills/atb-nnal-installer/SKILL.md 7.2 KB
- skills/atb-ops-to-aclnn-migration-workflow/SKILL.md 18 KB
- skills/atb-ops-to-aclnn-migration-workflow/TASK_TEMPLATE.md 8.0 KB
- skills/atb-testframework-build/SKILL.md 10 KB
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 · 196 lines · 90 tokens per session scan A 1d7740ddbbba
ascend-transformer-boost is a skill published in the GitHub repository Ascend/agent-skills (40 stars, last pushed 4mo ago), licensed MulanPSL-2.0. It adds 90 tokens to every session and 2,372 once invoked, about $0.0005 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
external-gitcode-ascend-ascend-transformer-boost
An index of skills for developing and deploying Huawei's Ascend Transformer Boost library, a set of tools for accelerating transformer-based AI models. It covers the main stages of working with Ascend NPUs and related operator libraries.
external-gitcode-ascend-atb-aclnn-operator-migration
A migration workflow for moving ATB operators to ACLNN, Ascend's operator library interface. It handles parameter mapping, runner implementation, device-based switching, and functional and performance checks.
external-gitcode-ascend-atb-debug-guide
A troubleshooting guide for ATB operator tests and Ascend NPU environments. It covers issues such as ABI mismatches, memory errors, failed CSV tests, and ACLNN interface problems.
external-gitcode-ascend-atb-nnal-installer
An installer for NNAL, an ATB acceleration library used with Ascend NPUs. It relies on an existing CANN Toolkit and Kernels environment.
external-gitcode-ascend-atb-aclnn-operator-replacement-designer
A design-document generator for replacing ATB operators with ACLNN operators, which are Ascend library interfaces. It turns interface documentation into a structured migration plan with parameter mappings, self-tests, and risks.
ascend-migration-analysis
A feasibility analysis for moving a PyTorch project from CUDA/GPU hardware to Ascend NPU hardware. It scans the code for hardware-specific dependencies and reviews device code, attention mechanisms, custom operations, distributed communication, precision, third-party packages, and compilation.