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/z80dev/lemon/verify-lemonnpx skills add z80dev/lemon --skill verify-lemongit clone --depth 1 https://github.com/z80dev/lemonWhat 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 | $0.00088 | $0.04166 |
| Opus 5 | $0.00044 | $0.02083 |
| Sonnet 5 | $0.00018 | $0.00833 |
| Haiku 4.5 | $0.00009 | $0.00417 |
Grade A, and why
verify-lemon 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.
How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Lemon
A runbook for verifying lemon behavior end to end. Work in three tiers and always prefer the lowest tier that can answer the question — most claims about routing, sessions, runs, delivery, and transport plumbing never need real Telegram.
| Tier | What it exercises | When |
|---|---|---|
| 1 DIRECT | Router, sessions, runs, bus events, control plane, delivery funnel | Default. Anything not Telegram-wire-specific |
| 2 FAKE TELEGRAM | The real Telegram transport + outbound, hermetically (no network) | Buttons, approvals, forum topics, markdown chunking, offset/poller semantics |
| 3 LIVE TELEGRAM | Real Bot API + real chat UX | Only for wire-level/UX claims the fake cannot prove |
If $ARGUMENTS is provided, scope the verification session to that feature.
Tier 1 — DIRECT (no Telegram)
Attaching to a running instance
Discover the node name and cookie from the beam process args (or fall back to
bin/lemon defaults: node lemon, cookie lemon_gateway_dev_cookie, control
plane 4040, web 4080, sim UI 4090):
More than one beam can be running (production + a disposable instance you
started, e.g. via scripts/product_smoke_local). NEVER pick one blindly —
list them, check the registered names, and select the node you actually mean:
epmd -names # every distributed node on this machine
ps -eo pid,args | grep beam.smp | grep -v grep | grep -o '\-sname [^ ]*'
Then extract the cookie from the args of that specific node's process:
# -sname and -setcookie are adjacent "<flag>\n<value>" pairs in the beam args
NODE=lemon_bot # <- the node you chose above, not just "the first beam"
ARGS=$(ps -eo args | grep beam.smp | grep -v grep | grep -- "-sname[= ]$NODE" | head -1 | tr ' ' '\n')
COOKIE=$(echo "$ARGS" | grep -A1 '^-setcookie$' | tail -1) # NEVER echo/print this
The read-only-on-production rule below depends on this selection being right:
if two nodes are up and you are about to mutate state, double-check you are
attached to the disposable one (its name will look like product_smoke_<pid>
or whatever --sname you passed).
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 · 326 lines · 88 tokens per session scan A 146f93978b47
verify-lemon is a skill published in the GitHub repository z80dev/lemon (129 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 4,166 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.