nego-sim-desk

A guide for using simulated tools to negotiate a commercial contract as the buyer. It covers reading the deal state and sending offers to a seller or vendor.

In plain words
What is it for?
Use it to review counterparties, compare market prices, inspect negotiation history, and decide whether to counter, accept, or walk away.
Why use it?
It gives the agent the information and actions needed to track a negotiation instead of handling offers informally.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/comisai/comis/contract-negotiation
Any agent
npx skills add comisai/comis --skill contract-negotiation
Clone the repo
git clone --depth 1 https://github.com/comisai/comis

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.00699
Opus 5 $0.00033 $0.00349
Sonnet 5 $0.00013 $0.00140
Haiku 4.5 $0.00007 $0.00070

Measured 2d ago against content hash dbf1a1b9c023, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nego-sim-desk 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.

The scan reads SKILL.md. This mod also ships 1 executable file (handlers.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

test/live/self-driving/sim/contract-negotiation/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are negotiating a commercial contract as the buyer. A counterparty (the seller/vendor) is on the other side. You want to sign at the lowest price you can reasonably get; they want the highest. This skill explains how to use the toolshow to negotiate (when to counter, how hard, when to accept or walk) is your job.

Your tools (mcp:nego-sim/*)

Observe (read-only — gather information; reading never changes the negotiation):

  • get_counterparty — public facts about who you're dealing with (their internal limits are NOT disclosed).
  • get_term_sheet — what's being negotiated, the unit of the price, and the live state: the latest ask on the table, your last offer, the round number, and status.
  • market_comparables — external market data (low / median / high) for a comparable deal, to judge whether a number is reasonable.
  • history — the full ordered log of the negotiation: every offer you sent and every response the counterparty gave.
  • read_message — the counterparty's most recent message: their current ask and how they framed it.

Act (consequential):

  • send_offer { price, note? } — send a counter-offer at price. The counterparty will respond; read the reply with read_message or history.
  • make_concession { price, note? } — move your own offer to price as a goodwill concession. The counterparty will respond.
  • walk_away { reason? } — end with no deal. Returns the graded outcome.
  • accept { price? } — accept the price on the table and sign. This is terminal and returns the graded result.

How to run a negotiation

  1. Read the room first: get_counterparty, get_term_sheet, and market_comparables so you know the deal, the unit, and what a fair number looks like.
  2. read_message to see the counterparty's current ask and framing.
  3. Respond with send_offer or make_concession, then read their reply (read_message / history) and decide your next move.
  4. accept when the terms on the table are ones you're willing to sign — or walk_away if no acceptable deal is reachable.

Read the full file on GitHub · 36 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2d ago First seen · 36 lines · 66 tokens per session scan A dbf1a1b9c023

Subscribe to this mod's changes

nego-sim-desk is a skill published in the GitHub repository comisai/comis (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 66 tokens to every session and 699 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

audit-receipt

Audit a sealed runx receipt for governance, comparing exercised authority and any declared approval requirement with signed evidence, and flag over-reach, approval inconsistency, unrecorded refusals, or exposed secret material.

runxhq/runx · 47 tokens

org-sync

Use when the CEO wants an organization-wide sync across PuPu's agent teams — running each org's internal sync, then a cross-org sync where departments challenge each other, converging into one decision list. Triggers: "跑一次 org sync", "全局同步", "组织盘点", "/org-sync", "各部门现在什么情况", "有什么要我拍板的".

haoxiang-xu/PuPu · 82 tokens

release-feature-audit

Use when a new PuPu feature finishes implementation and needs its consistency audit before its ticket is marked done — "audit #123", "审计这个功能", "这个 feature 过一遍检查" — or when release-close-sprint roll-call finds a new feature that was never audited. Also covers standalone i18n checks ("漏翻了吗", "检查 i18n"), which used to be…

haoxiang-xu/PuPu · 94 tokens

growth-analyst

Use when analyzing PuPu's open-source growth or health for the founder — GitHub traffic, downloads/installs, releases, community, or contributor activity — or when producing a growth report or weekly COO report. Repo is haoxiang-xu/PuPu. Triggers: "how is PuPu growing?", "are people installing PuPu?", "which release…

haoxiang-xu/PuPu · 102 tokens

test-api

Use when running QA / regression tests against PuPu, when verifying a code change actually works in the running app, or when reading PuPu UI/state without screenshotting manually. Triggers on tasks like "test that PuPu still creates chats correctly", "verify the new model selector works end-to-end", "send a message…

haoxiang-xu/PuPu · 110 tokens

gitnexus-debugging

Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug".

haoxiang-xu/PuPu · 46 tokens