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 commands/fourleafai/clover-public/negotiate-prepgit 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/negotiate-prep)<a href="https://agentmods.dev/commands/fourleafai/clover-public/negotiate-prep"><img src="https://agentmods.dev/badge/commands/fourleafai/clover-public/negotiate-prep.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02713 |
| Opus 5 | $0.00000 | $0.01357 |
| Sonnet 5 | $0.00000 | $0.00543 |
| Haiku 4.5 | $0.00000 | $0.00271 |
Grade B, and why
negotiate-prep scanned grade B with 1 finding 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.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
This is a research question, and you answer it with real data. Do not ask the user for an offer they don't have, and do not refuse to name a number. That's the dodge we're avoiding. `comp_coach` is the wrong tool here (i Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
negotiate-prep
Coach the user through compensation, end to end. This workflow spans the full range, from "what's a good salary for X" with no offer at all, to "here's my written offer, how do I negotiate", to "I have no idea what I'm doing, let's just talk it through."
This is a research tool, not just a negotiation script. When the user has an offer, comp_coach is the engine. When they're just asking what's normal for a role, comp_benchmarks is the engine: it runs a live web search server-side and returns a cited salary band. Either way you give them real data. You never dodge a comp question by asking for an offer they don't have or by refusing to name a number.
When to run
- User says "I got an offer", "how do I negotiate", "they asked for my expected salary", "is this offer any good", "I have two offers".
- User asks a market-rate research question with no offer: "what's a good salary for X", "what do non-profit SWEs make", "is $X good for a senior PM in Austin".
- User says something vaguer like "I don't know what I'm doing here" about comp.
The one tool that matters here
comp_coach (free, no paid plan needed). You give it the offer details, it returns a structured negotiation memo:
- totalCompAnalysis total comp math for year 1 and year 4, plus the delta vs their current comp
- marketComparison a percentile estimate with a confidence rating and a caveat about confirming against live data
- componentAnalysis base, equity, signing bonus, target bonus, benefits, each with an assessment, a room-to-negotiate rating, and specific talking points
- redFlags severity-tagged, each with why it matters and the exact question to ask before signing
- negotiationStrategy the primary lever to push, fallback levers, an exact opening move, and likely company responses paired with counters
- whatToAskBeforeSigning clarifying questions on equity refresh, review timing, promotion velocity, severance, change-of-control
- nextSteps a link to four-leaf.ai/comp-negotiation and a nudge to practice the conversation as a voice mock
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 First seen · 108 lines · 0 tokens per session scan B 4cc9228545d5
negotiate-prep is a command published in the GitHub repository fourleafai/clover-public (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,713 tokens. A static security scan graded it B with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.
config
Command "config" from sdebruyn/fabric-dw-mcp-cli, covering configuration & defaults, http retry budget, sql retry budget, mcp workspace allowlist {#mcp-workspace-allowlist} and mcp server log level.
deps-age
Analyze dependency freshness and maintenance activity.
setup
Diagnose-first project setup with state machine — scans, confirms, interviews, writes.
scan
Scan AWS account for cost optimization.
triage
Triage ServiceNow incidents — list open incidents, assess priority, investigate a specific INC, or analyze trends.