update-value-prop

update-value-prop is a command for coding agents from adidacta/pmf-detective. It costs 5 tokens per session (715 once invoked), scanned A, original, MIT.

A command for updating the Value Proposition section of a product-market-fit document. A value proposition explains who a product helps, what benefit it offers, and what action should follow.

In plain words
What is it for?
Use it to review or revise a value proposition, including its short description, desired future outcome, main message, call to action, and saved alternatives.
Why use it?
It checks whether the relevant file exists, shows its current contents, and guides the user through deciding what to change instead of editing an unknown document blindly.

Command

Part of the plan-pmf plugin — 9 skills, 6 commands shipped together

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 commands/adidacta/pmf-detective/update-value-prop
Clone the repo
git clone --depth 1 https://github.com/adidacta/pmf-detective

Or install plan-pmf, the plugin that ships this one along with the rest of its 9 skills, 6 commands.

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.

agentmods badge for update-value-prop

README.md
[![agentmods](https://agentmods.dev/badge/commands/adidacta/pmf-detective/update-value-prop.svg)](https://agentmods.dev/commands/adidacta/pmf-detective/update-value-prop)
Your own site
<a href="https://agentmods.dev/commands/adidacta/pmf-detective/update-value-prop"><img src="https://agentmods.dev/badge/commands/adidacta/pmf-detective/update-value-prop.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 715 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 $0.00005 $0.00715
Opus 5 $0.00003 $0.00358
Sonnet 5 $0.00001 $0.00143
Haiku 4.5 $0.00001 $0.00072

Measured 5d ago against content hash 0bf29d5e8ee9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-value-prop 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 5d 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.

commands/update-value-prop.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Value Prop

Update the Value Proposition section of your PMF context layer.

Instructions

  1. Check if pmf/value-prop.md exists

    • If exists: Read it and show summary, ask what to update
    • If not: Inform user and offer to create it
  2. If file exists, show current state:

┌───────────────────────────────────────────────────────────────┐
│  CURRENT VALUE PROPOSITION                                    │
├───────────────────────────────────────────────────────────────┤
│                                                               │
│  Callout: [3-part descriptor]                                 │
│  Magnet: [Desired future]                                     │
│  Message: [Selected value prop]                               │
│  CTA: [Call to action] → validation goal                      │
│                                                               │
│  Alternatives: [N] saved for A/B testing                      │
│                                                               │
└───────────────────────────────────────────────────────────────┘
  1. Use AskUserQuestion: "What would you like to update about your value proposition?"

Options:

  1. "The Callout" — description: "Refine what makes your ICP stop and say 'that's me'"

  2. "The Magnet" — description: "Refine the desired future / promised outcome"

  3. "The Message" — description: "Regenerate value prop options from current Callout + Magnet"

  4. "CTA" — description: "Update the call to action (your validation goal)"

  5. "Switch to an alternative" — description: "Promote a different angle to primary"

  6. "Start over completely" — description: "Rebuild from scratch using value-prop-builder"

  7. Handle each option:

Option 1: The Callout

  • Show current Callout (Identity, Context, Pain/Fear)
  • Run Phase B from value-prop-builder (generate new Callout options from ICP data)
  • After new Callout is set, regenerate value prop options (Phase D) and let user re-pick

Option 2: The Magnet

  • Show current Magnet
  • Run Phase C from value-prop-builder (generate new Magnet options from ICP data)
  • After new Magnet is set, regenerate value prop options (Phase D) and let user re-pick

Read the full file on GitHub · 82 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.

  1. 5d ago First seen · 82 lines · 5 tokens per session scan A 0bf29d5e8ee9

Subscribe to this mod's changes

update-value-prop is a command published in the GitHub repository adidacta/pmf-detective (18 stars, last pushed 6mo ago), licensed MIT. It adds 5 tokens to every session and 715 once invoked, about $0.0000 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 2026-08-30.