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 sisibeloved/cpython-optimize-skill --skill isa-instruction-lookupgit clone --depth 1 https://github.com/sisibeloved/cpython-optimize-skillWrote 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/sisibeloved/cpython-optimize-skill/isa-instruction-lookup)<a href="https://agentmods.dev/skills/sisibeloved/cpython-optimize-skill/isa-instruction-lookup"><img src="https://agentmods.dev/badge/skills/sisibeloved/cpython-optimize-skill/isa-instruction-lookup/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/sisibeloved/cpython-optimize-skill/isa-instruction-lookup"><img src="https://agentmods.dev/badge/skills/sisibeloved/cpython-optimize-skill/isa-instruction-lookup.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 | $0.00135 | $0.01288 |
| Opus 5 | $0.00068 | $0.00644 |
| Sonnet 5 | $0.00027 | $0.00258 |
| Haiku 4.5 | $0.00014 | $0.00129 |
Grade A, and why
isa-instruction-lookup 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 8d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ISA Instruction Lookup
查询官方 ISA 规格的统一入口。数据只来自权威来源,经离线 ingest 进入
mcp/isa-reference/data/isa.db,通过 MCP 工具只读查询。
当前库覆盖:
a64(2259 条,ARM-official XML 2026-06):编码/伪代码/FEAT_xxx全量x86_64(854 条 = Intel-SDM 771 + AMD-APM 特有 83):opcode 表/伪代码/CPUID:XXXfeature(Intel opcode 表 feature 列 + AMD 页内声明双源,约 1700 行)
何时用
- 读 JIT/反汇编机器码,要确认某助记符的编码、操作数约束或执行语义
- codegen 优化:找"做某件事"的指令(如条件选择、位反转、批量内存操作)
- 判断某指令依赖哪个
FEAT_xxx,目标环境(Kunpeng 等)是否实现 - 跨平台比对:某 A64 指令在 x86 侧的等价候选(或反向)
三层检索流程
按顺序降级,不要跳层:
- 意图映射:查询是优化意图(如"用条件选择取代比较和分支")时,先读
references/optimization-intent-map.md把意图翻译成功能术语(→ "conditional select")。 已知助记符(如反汇编输出里的CSEL)跳过此层。 - 功能检索:
find_instruction_by_function(description="conditional select")— FTS 匹配 brief/authored,返回候选列表。描述用英文功能术语。 候选检索跨 category/feature 不设限——优化替换经常跨执行域(base 需求 用 SIMD 指令满足、SVE 替换 base 序列),分类和 feature 只是可用性维度, 不是过滤条件。 - 精确查询与查证:候选定位后
lookup_instruction(mnemonic, verbose=True)。 查证主体与必做动作:operation_pseudocode——方案的每条语义假设("无条件写 Rd")逐行比对, 不一致即方案错误;asm_templates——合法语法形态,写汇编/lowering 的依据;operand_docs——操作数约束(宽度限制、内存源语义、编码位要求), 编码陷阱在这里暴露;bitfields——具体编码位。category只用于同名消歧,features只用于环境部署判定——这两者不是 语义查证的输出,只回答"是 base 类/无 feature 依赖"不构成查证。
跨平台等价:find_equivalent_instruction(mnemonic, from_arch, to_arch)。返回的是
词面候选(如 CMOVcc 的 a64 侧候选会混入 MOV 族)——先查
references/optimization-intent-map.md 的跨平台族映射(权威答案),机器候选用于
发现遗漏,精确等价性必须比对双方 operation_pseudocode 后下结论。
环境可用性判定
- 环境侧 feature 列表:a64 来自
/proc/cpuinfo或ID_AA64*系统寄存器解读 (环境审计走cinderx-env-validate);x86_64 来自 CPUID flag 名(如BMI2、SSE2),传入时带CPUID:前缀或由工具直接匹配 flag 名。 filter_by_environment(env_features=[...], arch=...)返回 available / conditional / unavailable。conditional表示该指令可用性还依赖 操作数取值(如 sz 字段),必须读该指令 bitfields 后人工判读。- 同名指令跨执行域变体(ABS 有 base/SIMD/SVE 三版)靠返回的
category消歧。
硬规则
- 库内
source_authority只允许官方来源白名单,规则见references/source-authority-policy.md。非官方来源数据一律不入库。 - 指令的微架构性能(吞吐/延迟)不在本库——ISA 手册不含性能数据,
性能结论走 perf/TRM 路径(
cinderx-isa-microarch-compare)。 - 引用指令规格时必须带上来源(
source_doc+page_start),便于回溯。 - 数据更新(新版本手册/新架构)只跑
mcp/isa-reference/scripts/ingest_*.py重建,不手改 isa.db。
What ships with it
2 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.
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.
- 8d ago First seen · 70 lines · 135 tokens per session scan A 57c81fc70bb6
isa-instruction-lookup is a skill published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 10d ago), licensed MIT. It adds 135 tokens to every session and 1,288 once invoked, about $0.0007 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.