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 agentmods add skills/arm/mcp/arm-enablementnpx skills add arm/mcp --skill arm-enablementgit clone --depth 1 https://github.com/arm/mcpWhat 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 | $0.00079 | $0.02260 |
| Opus 5 | $0.00039 | $0.01130 |
| Sonnet 5 | $0.00016 | $0.00452 |
| Haiku 4.5 | $0.00008 | $0.00226 |
Grade A, and why
arm-enablement 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 3d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arm Enablement
Evaluate an OSS repository for end-to-end Arm readiness and create:
arm-enablement-report.mdat the target repository root.arm-enablement-report.pdfexported from that Markdown source.
Write for OSS maintainers, developer-relations teams, and CNCF-style community audiences. Tell a concise case-study story while keeping every technical claim auditable.
Establish Scope
- Treat the current repository as the target unless the user supplies a GitHub URL.
- If a URL is supplied, clone it into an empty workspace or an
arm-enablement-target/subdirectory. - Prefer scanning the local target mounted at MCP
/workspace. Use the scanner'sgit_repoinput only for an initial report-only scan when the current workspace is unrelated to the target and there are no local or uncommitted changes to assess. Never usegit_repoto validate fixes; mount the changed checkout at/workspaceand omitgit_repo. - Default to report-only mode. Create only the two report files unless the user explicitly asks to apply fixes.
- If fixes are requested, make the smallest necessary source changes, update the report, and rerun affected checks. Do not commit unless the user asks.
- Record the repository URL, current commit, assessment mode, host architecture, and date.
Verify Arm MCP
Before assessing the project:
- Confirm that the configured
arm-mcpserver exposesmigrate_ease_scan,knowledge_base_search,check_image,skopeo,mca,apx_recipe_run, andsysreport_instructionsas applicable. - Treat these as MCP tools, not command-line programs. Do not search for similarly named executables on
PATH. - Confirm that the target checkout visible to Codex is the same checkout mounted at
/workspacein the Arm MCP container. Compare a distinctive file or the repository root listing. - If the server or workspace mapping is unavailable, stop and report the exact configuration problem. Point to the Arm MCP installation guide; do not fabricate scan results.
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.
- 3d ago First seen · 107 lines · 79 tokens per session scan A 541812e81f8c
arm-enablement is a skill published in the GitHub repository arm/mcp (91 stars, last pushed 3d ago), licensed Apache-2.0. It adds 79 tokens to every session and 2,260 once invoked, about $0.0004 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
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.
cli-anything-3mf
3MF mesh geometry editor — detect and resize cylindrical holes, repair meshes, compare 3D printing files. Works with BambuStudio and PrusaSlicer 3MF files.
platform-port
Guide porting FastLED to new MCU platforms, including int.h types, clockless drivers, SPI implementations, and platform detection. Use when adding support for a new microcontroller family or board.
doca-compress
Use this skill for hands-on DOCA Compress programming on a BlueField DPU, ConnectX NIC, or host with DOCA — enabling compress-deflate, decompress-deflate, decompress-lz4-stream, or decompress-lz4-block tasks on a docacompress context (the hardware supports DEFLATE both directions plus LZ4 decompress; LZ4 encode is NOT…
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
anta-validation
Validate Arista EOS network state with structured pass/fail verdicts using ANTA. Use for "is this switch healthy", "did my change break anything", "verify BGP/interfaces/hardware are correct", "run a health check on this device". Read-only. A test for a feature the device does not run reports notapplicable — never a…