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.
git clone --depth 1 https://github.com/fourleafai/clover-publicWrote 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/commands/fourleafai/clover-public/kickoff)<a href="https://agentmods.dev/commands/fourleafai/clover-public/kickoff"><img src="https://agentmods.dev/badge/commands/fourleafai/clover-public/kickoff/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/commands/fourleafai/clover-public/kickoff"><img src="https://agentmods.dev/badge/commands/fourleafai/clover-public/kickoff.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 | $0.00000 | $0.00738 |
| Opus 5.5 | $0.00000 | $0.00295 |
| Sonnet 5.5 | $0.00000 | $0.00148 |
| Haiku 4.5 | $0.00000 | $0.00074 |
Grade A, and why
kickoff 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 1mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/kickoff
Default entry. Figure out what the user is prepping for, confirm Four-Leaf has data for it, route to the right command.
When to run
- User opens a fresh conversation and says something generic like "help me with my job search" or "I have an interview coming up".
- User's intent doesn't map cleanly to one of the other six workflows.
Flow
-
Verify the MCP is connected. Call
list_roles. If it fails with a not-connected error, tell the user how to install the MCP (seemcp-tools.mdfor the message) and offer coaching-only mode while they fix it. Step 2'slist_applicationscall proves the connection just as well, so if you're doing both, one of them is enough. -
Check whether they're already mid-search. Call
list_applications. It's free, unmetered, and takes no arguments, so it costs nothing to ask. If it comes back with rows, the user isn't starting from zero and the greeting shouldn't pretend they are. Open on what's actually live:You've got three applications open, one interviewing at Stripe. Want to prep that one, or are we adding to the pile?
If it comes back empty, greet briefly instead. One sentence, not a wall of text:
Four-Leaf coach here. What are you working on? Finding jobs, prepping for a specific interview, scoring your resume, or thinking about negotiation?
Don't read the whole list out. Name the one or two that matter (anything
interviewing, then the most recently updated) and let them pick. If the user asked a direct question like "where am I", answer it with the list and skip the routing question entirely. -
Get the four pieces of context that matter. Don't ask all of them upfront, and don't ask for what the tracker already told you. Ask the one that's most relevant to whatever the user said:
- Role, the position they're targeting (data scientist, software engineer, product manager, etc.). If they name a role, validate it against
list_roles. - Company, the specific target if they have one.
- Seniority, one of entry, mid, senior, or staff.
- Timeline, since interview tomorrow vs. browsing the market matters a lot.
- Role, the position they're targeting (data scientist, software engineer, product manager, etc.). If they name a role, validate it against
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.
- 1mo ago Changed · +8 lines 704a4cf3126d
- 1mo ago First seen · 41 lines · 0 tokens per session scan A 639c0ea6a47d
kickoff is a command published in the GitHub repository fourleafai/clover-public (8 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 738 tokens. 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 2026-08-31.
Other commands, from other repositories
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
watch
You are executing the /hydra:watch command. Live monitoring of all background agents with real-time status updates.
render
Inspect an archived transcript (gzipped) — show counts, tool calls, errors. Useful after a PreCompact or SessionEnd, before deciding to write a retroactive /continuum:checkpoint.
golden-path
The golden path. One command, idea to merged PR. Runs the full pipeline, prd → prp → plan → dev → test → pr, with sensor + eval gates at every stage.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
gws-people
Search and look up Google Contacts and directory profiles.