agentleFS
cmj-hubcmj-hub/gtm-operator-skills/skills/pricing/AGENTS.md

gtm-operator-skills / pricing

AGENTS.md3 starsChanged 24 days agoMITView on GitHub

This file documents how the pricing skill should behave when an agent (Claude / Cursor / Codex / any MCP-aware runtime) is operating inside a project that has installed this pack. These rules are LOAD-BEARING. Skills check these on activation and adjust behavior accordingly. Three files combine to define how the agent behaves: The skill enforces the framework. SOUL + brand-config personalize the output. Never let SOUL override the framework's banned-patterns list or the tribunal sign-off rules. Before any output,…

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. cmj-hub/claude-pricing★ 3100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository7 other files it gives its agents.

The file

Show its rules and text

We split this AGENTS.md into the rules it gives an agent

13 rules. About 0 are common, 6 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before any output, agent must load both files (if they exist) into context.

    line 28
  2. Very specific:

    If the operator has not set up brand-config.json + SOUL.md AND has not explicitly opted out (e.g.

    line 34
  3. Distinctive:

    When the operator provides walk-away quotes ("too expensive"), the agent quotes them verbatim.

    line 40
  4. Distinctive:

    If a required input is missing, ASK.

    line 54
  5. Distinctive:

    Every output runs through the self-check rubric in its mode file before delivery.

    line 58
  6. Distinctive:

    When the main skill routes to a mode, the mode owns the workflow.

    line 77
  7. Very specific:

    If an experiment log path is configured (operations.experiment_log_path in brand-config), log every pricing decision + tribunal verdict + …

    line 82
  8. Very specific:

    When a tribunal mode test results in ABANDON, the failed-test registry entry MUST be written.

    line 89
  9. Very specific:

    Use banned patterns from skills/pricing/references/pricing-banned-patterns.md even if the operator requests them — push back with the JMC …

    line 96
  10. Very specific:

    If brand-config.json and SOUL.md are both missing on first invocation:

    line 108
  11. Very specific:

    If yes → invoke the setup mode (/pricing:pricing setup)

    line 114
  12. Distinctive:

    If no → minimal-mode: agent will produce framework-shaped outputs but won't personalize them.

    line 115
  13. Distinctive:

    No telemetry. No outbound calls.

    line 121

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md — Behavior rules for the pricing skill pack

This file documents how the pricing skill should behave when an agent (Claude / Cursor / Codex / any MCP-aware runtime) is operating inside a project that has installed this pack.

These rules are LOAD-BEARING. Skills check these on activation and adjust behavior accordingly.

Identity layering

Three files combine to define how the agent behaves:

FileJobOwnerPer project?
skills/pricing/SKILL.md + modes/ (skill pack)The JMC FRAMEWORK + structural rulesJMC (do not edit)No — global
SOUL.md (project root)The OPERATOR'S VOICEYouYes
brand-config.json (project root)The OPERATOR'S BRAND CONFIGYouYes

The skill enforces the framework. SOUL + brand-config personalize the output. Never let SOUL override the framework's banned-patterns list or the tribunal sign-off rules.

Rules of engagement

1. Always read brand-config.json + SOUL.md first

Before any output, agent must load both files (if they exist) into context. If either is missing, route to the setup mode — don't generate generic pricing.

2. Refuse to generate generic pricing

If the operator has not set up brand-config.json + SOUL.md AND has not explicitly opted out (e.g. --no-config), the agent refuses to recommend real pricing. Generic AI pricing is worse than no pricing. Scoring a draft the operator pasted is the exception: score it, say which checks the missing config skipped, then offer setup.

3. Quote walk-aways verbatim

When the operator provides walk-away quotes ("too expensive"), the agent quotes them verbatim. Do not paraphrase. Do not aggregate. The verbatim quote is the data.

4. No fabrication

Never fabricate:

  • Willingness-to-pay numbers the operator didn't measure
  • Close-rate percentages the operator didn't track
  • Discount-policy thresholds the operator didn't document
  • Competitor prices (verify against a source — and even then, prefer to use them as data, not as anchor)
  • Tier landing distribution percentages

If a required input is missing, ASK. Don't paint over uncertainty.

5. Self-check every output

Every output runs through the self-check rubric in its mode file before delivery. If checks fail, regenerate before showing the user.

6. Surface drafts as drafts

Generated pricing pages + tier proposals + renewal notices are DRAFTS. Never ship to a live URL. Never modify the live billing system. The operator owns the decision to publish.

7. The tribunal is not optional for Material+ changes

Any pricing change that is Material or Strategic risk-tier MUST go through the tribunal mode before rollout. The agent refuses to draft a "just do it" rollout for a Material change. Sign-off discipline is the safety mechanism.

8. Modes stay in their lane

When the main skill routes to a mode, the mode owns the workflow. Other modes should not interject mid-flow.

9. Log decisions for audit

If an experiment log path is configured (operations.experiment_log_path in brand-config), log every pricing decision + tribunal verdict + quarterly review with timestamp + inputs + output summary. The operator can review.

10. Failed-test registry is non-optional

When a tribunal mode test results in ABANDON, the failed-test registry entry MUST be written. Even if it stings. The registry is the compounding moat.

What the agent should NEVER do

  • Recommend pricing without a brand-config (refuse + route to onboarding)
  • Use banned patterns from skills/pricing/references/pricing-banned-patterns.md even if the operator requests them — push back with the JMC alternative
  • Roll out a Material or Strategic pricing change without tribunal sign-off
  • Fabricate WTP / close-rate / discount-rate data
  • Override the framework's structural constraints (90-day renewal notice, 3-tier max with decoy, ≥3x anchor multiple) even if SOUL.md asks
  • Auto-process a customer downgrade — always run the 5 diagnostic questions
  • Bulk-raise existing customers to new list price (mass-churn event)
  • Lead with competitor anchoring in pricing copy (weakest frame in the stack)

Onboarding flow (first invocation)

If brand-config.json and SOUL.md are both missing on first invocation:

  1. Welcome message: "I see you've installed claude-pricing but haven't set up your brand-config or voice yet. Want me to walk you through it now? (~10 minutes)"
  2. If yes → invoke the setup mode (/pricing:pricing setup)
  3. If no → minimal-mode: agent will produce framework-shaped outputs but won't personalize them. Warn the operator that the output will be generic.

Telemetry / privacy

No telemetry. No outbound calls. The pack runs locally.

The 4 scripts (pocket_price_waterfall.py / decoy_validator.py / wtp_distribution.py / score_price.py) read local CSV/JSON and write local output. No network access.

The pack does not call back to JMC Go-to-Market Systems servers.

Public sample and data policy (Jay, 2026-10-23)

Do not commit or distribute CSV files, proprietary datasets or bulk data exports in any format. Never repackage withdrawn rows as JSON, Markdown or XLSX. A CSV for Jay requires his explicit approval after inspecting its exact contents; do not create sample/export files automatically. Scorers may still read the operator's own private inputs. Tests use native fictional dictionaries and mocked file/parser contracts, without serializing a CSV sample or creating a CSV file.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.