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/aemcoder/skills/migrate-headernpx skills add aemcoder/skills --skill migrate-headergit clone --depth 1 https://github.com/aemcoder/skillsWhat 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 | $0.00043 | $0.07044 |
| Opus 5 | $0.00022 | $0.03522 |
| Sonnet 5 | $0.00009 | $0.01409 |
| Haiku 4.5 | $0.00004 | $0.00704 |
Grade B, and why
migrate-header scanned grade B with 2 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
> a sudo prompt for `/.playwright` on the first `playwright-cli` call, that is Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`data:image/svg` URI: fetch it (`curl -fsSL -- "{logo.src}"`) and check How it starts
The opening of the file, as written. The whole thing — 763 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate Header to EDS
Migrate a website's header/navigation into the EDS header block pattern.
Produces nav.plain.html + customized header.css. The header JS is
typically pre-built in the EDS repo — you customize CSS only.
HARD CONSTRAINTS
- Output is
nav.plain.html— NOT a regular block.plain.html. - Block name is
header— CSS/JS atblocks/header/header.css|.js. - If
blocks/header/exists in the repo, keep the existing JS. Only generatenav.plain.htmland customizeheader.css. - CSS specificity: ALL rules must be
.header.blockscoped. NOT.header— must be.header.blockto prevent global overrides. - NEVER inline CSS or JS in the preview. Use the EDS framework.
- NEVER pre-decorate HTML. No
.section,.block,data-block-name.
Parameters (from cone's feed_scoop prompt)
sourceUrl— URL of the source pageprojectPath— EDS project path (e.g.,/shared/vibemigrated)bounds— bounding box of the header regionnotes— decomposition notes (e.g., "two-tier purple header")
Step 1: Capture Source Header
Navigate to the source page and extract the header's content:
Browser access: driving playwright requires
write: /.playwright/**. The orchestrator should pre-authorize this before dispatching you; if you hit a sudo prompt for/.playwrighton the firstplaywright-clicall, that is expected — it should be granted with analwaysrule so it does not recur.
playwright-cli tab-new {sourceUrl}
Capture the targetId from the output (e.g., ABC123). All subsequent
playwright-cli commands for this tab MUST include --tab={sourceTabId}.
MANDATORY — resize to a desktop viewport before ANY screenshot or extraction:
playwright-cli resize --tab={sourceTabId} 1440 900
New tabs open at a default viewport of ~780px (a mobile breakpoint). Capturing or measuring the component at that width yields a mobile-layout screenshot and can drive wrong fidelity decisions (e.g. baking a mobile breakpoint into the block CSS). Never skip this. Optionally hard-fail if the resize did not take:
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.
- yesterday First seen · 763 lines · 43 tokens per session scan B 193d004b806e
migrate-header is a skill published in the GitHub repository aemcoder/skills (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 43 tokens to every session and 7,044 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
speckit-analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
add-sample
Create a SamplesApp sample page with correct theming and attributes. Use when adding UI samples for controls.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…