Borrowing it
Nothing to install: this file belongs to gke-labs/kube-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gke-labs/kube-agents/main/.agents/skills/edit-mirrored-skill/SKILL.mdgit clone --depth 1 https://github.com/gke-labs/kube-agentsWrote 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/gke-labs/kube-agents/edit-mirrored-skill)<a href="https://agentmods.dev/skills/gke-labs/kube-agents/edit-mirrored-skill"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/edit-mirrored-skill/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/gke-labs/kube-agents/edit-mirrored-skill"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/edit-mirrored-skill.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 | $0.00057 | $0.02343 |
| Opus 5.5 | $0.00023 | $0.00937 |
| Sonnet 5.5 | $0.00011 | $0.00469 |
| Haiku 4.5 | $0.00006 | $0.00234 |
Grade A, and why
edit-mirrored-skill 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Change a mirrored skill so the change survives upstream syncs and make skills-check passes.
This skill is the procedure; docs/designs/upstream-skill-overlays.md
is the design and its rationale. scripts/skill_overlay.py is the tool behind the
make skills-* targets.
A skill is mirrored when agents/platform/skill-overlays/<skill>/upstream.lock exists. It has
three layers:
| Layer | Path | Edit by hand |
|---|---|---|
| Upstream copy | third_party/google-skills/<skill>/ |
never; only the tool writes it and the lock |
| Overlay | agents/platform/skill-overlays/<skill>/ |
patch headers, append.md, deleting a file |
| Shipped skill | agents/platform/skills/<skill>/ |
yes, then record it with skills-refresh |
The shipped skill is the copy with the patches applied in filename order, then append.md. It
is committed, and it is what the agent reads. skills-refresh writes patch bodies and
append.md from your edits; skills-sync and skills-continue rewrite the copy, lock, patches
and shipped skill; skills-generate rebuilds the shipped skill.
Rules
- Never edit
third_party/google-skills/orupstream.lockby hand. CI compares both withgoogle/skills. If a sync reports that upstream renamed or removed the skill, stop and ask a maintainer. - Keep one patch per reason. Fold a follow-up edit into the patch with the same reason.
- Put an upstream sync in its own pull request, with no other edit than the patches it needs to
pass the checks (conflict resolutions, a
make shellcheckfix). - Never delete a patch to get past a conflict. Drop one only when upstream's new text covers its
Why:, and say so in the pull request. - Keep
MSG=to plain words: the Makefile passes it through the shell, so backticks and double quotes break. Edit theSubject:line in the patch afterwards if it needs code formatting. - Run
make skills-checkbefore committing; commit the shipped skill and its overlay together. - Treat a skill's scripts like its Markdown: edit the shipped script and record it with
make skills-refresh.make shellchecklints the shippedgke-*scripts. Fix a finding in a patch; add# shellcheck disable=SCnnnn # reason(also in a patch) only for a false positive, or when the fix would change what upstream's script does. If a sync brings in a new finding, add that patch in the same pull request. Put tests for those scripts intests/(Where Tests Go); a file in the skill folder that no patch produces failsmake skills-check. - Run
make docs-generatewhen a skill is added or a frontmatterdescriptionchanges, and commit the regenerated skill catalogue. Runmake docs-checkbefore pushing. - Expect the
Docker Buildcheck (the platform image build), notmake skills-check, to run every shell block of the shipped skills throughdeploy/docker/check_skill_commands.py. If an edit or sync changes a block listed in itsKNOWN_FINDINGS, update the entry in the same pull request; rewrite a command Tirith refuses in a patch. - Follow the eval loop (
.agents/rules/eval_driven_development.md) for any change to what the agent reads: adding, changing or removing a patch orappend.md, or a sync. A change that leaves every shipped skill byte-identical, or a patch that only fixes a lint finding in a script without changing what it does, states that exemption in one line under Live validation. - Leave stopping mirroring (deleting a skill's copy, lock and overlay) to a maintainer.
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 Changed · +1 lines 7f07607a6d3d
- 13d ago Changed · +10 lines 06e6ce1be522
- 16d ago Changed · -13 lines d4f080fd68a4
- 17d ago First seen · 148 lines · 57 tokens per session scan A 372ac512711f
edit-mirrored-skill is a skill published in the GitHub repository gke-labs/kube-agents (116 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 2,343 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-10.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…