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 skills add petergaultney/lemonaid --skill briefgit clone --depth 1 https://github.com/petergaultney/lemonaidWrote 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/petergaultney/lemonaid/brief)<a href="https://agentmods.dev/skills/petergaultney/lemonaid/brief"><img src="https://agentmods.dev/badge/skills/petergaultney/lemonaid/brief/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/petergaultney/lemonaid/brief"><img src="https://agentmods.dev/badge/skills/petergaultney/lemonaid/brief.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 | $0.00050 | $0.03729 |
| Opus 5.5 | $0.00020 | $0.01492 |
| Sonnet 5.5 | $0.00010 | $0.00746 |
| Haiku 4.5 | $0.00005 | $0.00373 |
Grade A, and why
brief 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 4d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keep your brief current
Your user reads your brief through lemonaid brief show, the inbox's b key, or tmux's prefix+b. Keep Status: and ## Now current so they can tell whose move comes next. Read the whole brief before editing it: its goal, limits, and output still apply.
Find or create your brief
Run lemonaid brief show --self. Your brief is the file attached to your session, normally in ~/.lemons/brief/. If none is attached but an older .z/brief*.md in your place is clearly yours, move it into that folder with a dated name for the work and run lemonaid brief attach --self <file>.
If you have no brief, run lemonaid brief new --self "<what the work is>". It creates a dated file and attaches it to you. Give it a task title, ## Now, and a short ## Goal saying what done looks like. Leave out Parent: when nobody assigned the work. Keep any generated ID line unchanged.
Name the session for the work, with a short area and change, rather than the brief filename or a personal name: lemonaid inbox rename --self "<area and change>". A launch prompt should name the work first, then point to the brief.
Choose the status
Set Status: only when one of the words below applies, and leave it out otherwise. Without one, lemonaid shows your own state: active while you are mid-turn, idle between turns, and deaf or dead if a message sent to you would not be read. lemonaid brief status --self clear removes a status that no longer applies. Older briefs may say working or waiting; both read as no status, and setting either clears it.
Status: contains exactly one word. The reason goes in ## Now. Choose by whose move it is:
| Status | When to use it |
|---|---|
running |
Nothing waits on your user and you are monitoring a named long process. Put the process and its session:window under ### Running. |
review |
A teammate's approving review on GitHub comes next, rather than your user's or a lemon's. Name the teammate and PR under ### Needs <who>. |
blocked |
Your user can act now: a decision, answer, review, trial, or text to post. Name the move under ### Needs <who>. Asking your user in your final message counts too. |
alert |
Your user's move is needed and harm grows while it waits. Keep this rare; importance alone does not qualify. Say what is getting worse under ### Needs <who>. |
merge |
Only your user's merge remains: reviewer approved, CI green, out of draft, and no conflicts. Check gh pr view <n> --json mergeable says MERGEABLE every time you set this. |
approve |
You reviewed a teammate's PR and recommend your user's approval on GitHub. Name the PR and review doc under ### Needs <who>. A review of a lemon's PR sets no status while it waits on its author or merge. |
done |
Your PR merged or closed, or your output was accepted, and no work or waiter remains. |
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.
- 4d ago Changed · +10 lines 1dcc2c2f40f4
- 5d ago Changed · +11 lines 444de6b27350
- 7d ago Changed · +2 lines 82f6b4df51ca
- 9d ago Changed · +3 lines 7fe0ccb0f46d
- 10d ago Changed 619893d5dddd
- 11d ago First seen · 123 lines · 50 tokens per session scan A 3f2588f6d1f8
brief is a skill published in the GitHub repository petergaultney/lemonaid (11 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 3,729 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 2026-10-09.
Other skills, from other repositories
hugging-face-paper-publisher
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
intake
Inspect configured Sources and propose evidence-backed Backlog work.
devtu-docs-quality
TOP PRIORITY skill — find and immediately fix or remove every piece of wrong, outdated, or redundant information in ToolUniverse docs. Wrong code, broken links, incorrect counts, and overlapping instructions must be fixed or removed — never left in place. Runs five phases: (D) static method scan, (C) static tool-call…
team-lead
Run a goal as a team when you can also do the work yourself: decide what you keep, dispatch the rest, and keep the status board honest. The delta over goal-conductor, which carries the dispatch, patrol and acceptance procedure this one points at. Load it when you are handed a goal, not a task.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
taskmarket-delegate
Delegate work to the TaskMarket agent-worker market - browse open tasks, create tasks with explicit authorization, and track/submit work, so an agent can outsource instead of burning inference on unreliable or low-confidence work.