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/fgrehm/lmk/skillnpx skills add fgrehm/lmk --skill skillgit clone --depth 1 https://github.com/fgrehm/lmkWhat 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 | $0.00080 | $0.00548 |
| Opus 5 | $0.00040 | $0.00274 |
| Sonnet 5 | $0.00016 | $0.00110 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
lmk 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 2d 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.
What it actually says
lmk — notify on completion
When the user has asked to be notified on completion, run lmk once, after the task is fully done (whether it succeeded or failed). The dialog pops on the user's desktop; they may be AFK.
Command
lmk -m "<one-line summary>"
- Summary should be short (under ~80 chars), factual, and say what finished.
- Include success/failure state if relevant. Use "✅" for success, "❌" for failure.
- If the user said "make sure I see it" / "don't let me miss it" / similar, add
-a(ack mode) — it re-prompts until the user clicks Ack.
Examples
User: "run the tests and lmk when done" → Run the tests. Then:
lmk -m "✅ tests passed (142 ok, 0 failed)"
or on failure:
lmk -m "❌ tests failed — 3 failures in auth_test.go"
User: "fix the flaky test and lmk" → Fix it, confirm it works, then:
lmk -m "✅ flaky test fixed — rerun 10x clean"
User: "lmk when the build's done, don't let me miss it" → Run the build, then:
lmk -a -m "✅ build done"
Rules
- Only once, at the end. Do not run
lmkbetween subtasks or as progress updates. The dialog is intrusive. - Do not run
lmkif the user did not ask for notification — this skill only activates on explicit "lmk" / "notify me" / "let me know" phrasing. - Do not use
lmk <command>form (i.e.lmk npm test) inside the skill — run the command yourself, then calllmk -mwith the result. You need to see the output to summarize it. - Summarize what happened, not what was asked. "tests passed" is better than "ran the tests you asked for".
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.
- 2d ago First seen · 50 lines · 80 tokens per session scan A 98919917dfce
lmk is a skill published in the GitHub repository fgrehm/lmk (21 stars, last pushed 4mo ago), licensed MIT. It adds 80 tokens to every session and 548 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
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…