What is mutual-action-plan?

A shared deal plan built with a buyer by working backward from the date they need the product to deliver value.

Use it to map milestones such as the buying decision, security review, contract, purchase order, and go-live.

It makes owners, deadlines, and approval steps visible before procurement, legal, security, or other delays threaten the target date.

mutual-action-plan — Skill for Claude Code by Doris-Labs/sales-skills

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.

Any agent

npx skills add Doris-Labs/sales-skills --skill mutual-action-plan

Clone the repo

git clone --depth 1 https://github.com/Doris-Labs/sales-skills

Made for: Claude Code.

Or install sales-skills, the plugin that ships this one along with the rest of its 30 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/doris-labs/sales-skills/mutual-action-plan/github.svg)](https://agentmods.dev/skills/doris-labs/sales-skills/mutual-action-plan)

Your own site

<a href="https://agentmods.dev/skills/doris-labs/sales-skills/mutual-action-plan"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/mutual-action-plan/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/doris-labs/sales-skills/mutual-action-plan"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/mutual-action-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,697 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00075	$0.01697
Opus 5.5	$0.00030	$0.00679
Sonnet 5.5	$0.00015	$0.00339
Haiku 4.5	$0.00007	$0.00170

Measured 2mo ago against content hash 653b9e92c290, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mutual-action-plan 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 2mo 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.

skills/mutual-action-plan/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mutual Action Plan

Purpose

Turn a target go-live date into a shared, dated plan the buyer co-owns — so the path to close is explicit, every step has a named owner on both sides, and the hidden gates (decision, procurement, legal, security) surface before they slip the date.

Inputs

The buyer's target go-live / "value by" date (the only date that matters — work back from it)
Stakeholders on both sides and their roles (champion, EB, procurement, legal, security, IT)
The deal's current stage and what's already committed
Known process requirements (security review, MSA/redlines, vendor onboarding, budget approval)

Method

Anchor on the go-live date, not the close date. Ask the buyer: "When do you need this delivering value?" Close date is derived, not chosen.
Backward-plan the milestones. From go-live, subtract each step's lead time to place it on the calendar. Don't forward-plan from today — that hides the slack you don't have. Typical chain (work right-to-left):
- Go-live / onboarding kickoff
- Contract signed
- Procurement / PO issued
- Legal redlines + MSA executed
- Security / InfoSec review passed
- Verbal commit / decision made
- Business case approved by EB
- Technical validation / POC complete
Assign an owner on BOTH sides for every milestone. A milestone with only a seller owner is a wish; one with only a buyer owner is a hope. Each row names a seller owner and a buyer owner. Buyer-only steps (procurement, legal, security) still get a seller owner who chases.
Surface the non-sales gates explicitly. Decision, procurement, legal, and security are where deals die silently. Each gets its own row with realistic lead time:
- Decision: who signs off, what they need to see, by when
- Procurement: vendor onboarding, PO process, payment terms, portal setup
- Legal: MSA/DPA, redline rounds (assume ≥2), who in legal owns it
- Security: InfoSec questionnaire, SOC2/pen-test review, SSO/data requirements
Make it a shared document, not a slide. The MAP lives where the buyer can see and edit it (shared doc / deal room). Use the table format below.
Get the buyer to co-own it. Co-ownership is earned, not asked for:
- Build the first draft with the champion live on a call, not for them in advance.
- Ask them to fill in the buyer-side owners and dates — their handwriting on it is the commit.
- Frame it as protecting their go-live date: "If we miss security by the 14th, your March launch slips — let's make sure that doesn't happen."
- Send it after every call with the status column updated; it becomes the shared truth.
- A champion who won't engage with the MAP is telling you the deal isn't real.

Read the full file on GitHub · 114 lines

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.

2mo ago First seen · 114 lines · 75 tokens per session scan A 653b9e92c290

Subscribe to this mod's changes

mutual-action-plan is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 1,697 once invoked, about $0.0003 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 2026-08-31.

Marketing and SEO Planning account-executive ai-agents anthropic claude claude-skills crm

mutual-action-plan next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mutual-action-planDoris-Labs/sales-skills	Skill	3	5mo ago	MIT	A	75	Claude Code
lynquGravisun/lynqu-ai-toolkit	Skill	6	11d ago	none	A	40	Claude Code, Codex
lynqu-sales-followupGravisun/lynqu-ai-toolkit	Skill	6	11d ago	none	A	39	Claude Code, Codex
lynqu-deal-deskGravisun/lynqu-ai-toolkit	Skill	6	11d ago	none	A	48	Claude Code, Codex
lynqu-event-blitzGravisun/lynqu-ai-toolkit	Skill	6	11d ago	none	A	47	Claude Code, Codex
lynqu-lead-managementGravisun/lynqu-ai-toolkit	Skill	6	11d ago	none	A	40	Claude Code, Codex
lynqu-outreachGravisun/lynqu-ai-toolkit	Skill	6	11d ago	none	A	41	Claude Code, Codex