Agent skill

Prd V03 Pricing Model

by mattgierhart in mattgierhart/PRD-driven-context-engineering

Select and validate pricing model for PRD v0.3 Commercial Model.

MITAuto-check passedProduct & Project Management

Install Prd V03 Pricing Model

skills CLI
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v03-pricing-model -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v03-pricing-model --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/prd-v03-pricing-model .claude/skills/prd-v03-pricing-model && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
prd-v03-pricing-model
GitHub stars
180
Token cost
~3k tokens
SKILL.md length
911 words
Files
3 (incl. references, assets)
Skills in repo
45
Repo updated
First seen
Licence
MIT

At a glance

Select and validate pricing model for PRD v0.3 Commercial Model.

  • Works in 5 steps: Calculate cost floor: What's minimum… → Identify anchor: What do customers pay… → Design tiers: Entry + Pro minimum; free… → …
  • Requests to set pricing
  • SKILL.md covers Consumes, Produces, Core Principle and Pricing Model × Product Type…, plus 12 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prd V03 Pricing Model is an agent skill from mattgierhart/PRD-driven-context-engineering. Select and validate pricing model for PRD v0.3 Commercial Model. Triggers on requests to set pricing, choose monetization model, design pricing tiers, validate willingness to pay, or when user asks "how much should we charge?", "what pricing model?", "freemium vs paid?", "how to structure tiers?", "price point?". Consumes Competitive Landscape (CFD-) and Product Type (BR-) from v0.2. Outputs BR- entries for pricing rules, tier boundaries, and competitive positioning.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files and assets (for example `assets/br-pricing.md` and `references/examples.md`).

It sits in Product & Project Management, covering Pricing strategy and PRD writing. The repository describes itself as: PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD… The licence is MIT.

When your agent uses it

  • Requests to set pricing
  • Choose monetization model
  • Design pricing tiers
  • Validate willingness to pay

Example prompts

  • “how much should we charge?”
  • “what pricing model?”
  • “freemium vs paid?”
  • “/prd-v03-pricing-model”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Grep, WebSearch, WebFetch

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Calculate cost floor: What's minimum price for positive unit economics?
  2. Identify anchor: What do customers pay today? (competitor or workaround)
  3. Design tiers: Entry + Pro minimum; free only if strategic
  4. Test WTP: Landing page with price, measure signup conversion
  5. Lock BR- entries: Document as enforceable rules

What it can do on your machine

Read from SKILL.md and the folder at commit 30ed1b0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Glob
    • Grep
    • WebSearch
    • WebFetch

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prd V03 Pricing Model loads about 3k tokens when it runs, and up to ~4.7k if it reads all its reference files. Until then it costs about 123 tokens; SKILL.md has 911 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~123
When it runs · the whole SKILL.md, loaded when a task matches
~3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mattgierhart/PRD-driven-context-engineering at commit 30ed1b0, republished under its MIT licence (© mattgierhart). 911 words, ~2,963 tokens.

Download SKILL.mdSave it as .claude/skills/prd-v03-pricing-model/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
prd-v03-pricing-model
description
Select and validate pricing model for PRD v0.3 Commercial Model. Triggers on requests to set pricing, choose monetization model, design pricing tiers, validate willingness to pay, or when user asks "how much should we charge?", "what pricing model?", "freemium vs paid?", "how to structure tiers?", "price point?". Consumes Competitive Landscape (CFD-) and Product Type (BR-) from v0.2. Outputs BR- entries for pricing rules, tier boundaries, and competitive positioning.
allowed-tools
Read, Write, Edit, Glob, Grep, WebSearch, WebFetch
context
fork

Pricing Model Selection

Position in HORIZON workflow: v0.2 Product Type Classification → v0.3 Pricing Model Selection → v0.3 Moat Articulation

Consumes

This skill requires prior work from v0.2-v0.3:

  • BR-* product type entry (from Product Type Classification) — Determines which pricing model makes sense
  • CFD-* competitive intelligence entries (from Competitive Landscape Mapping) — Competitor pricing, WTP signals
  • BR-* moat entries (from Moat Definition, parallel v0.3 work) — Price as potential moat element
  • KPI-* outcome entries (from Outcome Definition, parallel v0.3 work) — Success metrics tied to pricing
  • Cost structure estimates (from own analysis) — Unit economics to validate price floors

This skill assumes v0.2 competitive analysis is complete and product type is defined.

Produces

This skill creates/updates:

  • BR-PRC-* entries (pricing constraints) — Rules governing price floors, ceilings, discounts
  • BR-PKG-* entries (packaging rules) — Tier boundaries and feature gates
  • BR-CMP-* entries (competitive positioning) — Price anchor targets and undercut thresholds
  • Pricing model artifact — Named decision: "We will use [Model] because [evidence]" with tier definitions

All BR pricing entries should include:

  • confidence: 2-3/5 (based on WTP evidence tier and competitor benchmarks, not assumptions)
  • Evidence source (competitor pricing, customer interviews, cost structure)
  • Forward target: "Would move to 4/5 if real customers validate WTP"

Example pricing rule entry:

markdown
BR-PRC-001: Entry Price Floor

Rule: Entry tier never below $15/mo (annual) or $19/mo (monthly)
Confidence: 2/5 (source: CAC-estimate + competitor-benchmarks)
Rationale: Below $15/mo, CAC payback exceeds 6 months, unsustainable
Enforcement: Stripe product configuration, pricing page, contract templates
Evidence:
  - CFD-042 (competitor pricing): Similar tools start at $15-25/mo
  - KPI-001 (outcome): CAC estimate $45, need 3-month payback = $15/mo minimum
Enforcement: Set in Stripe, document in pricing page, enforce in sales contracts
Exception: Founding customer 50% discount (must be approved by founder)
Next Target: "Would move to 4/5 if 5+ paying customers validate willingness at $15/mo"

---

BR-CMP-002: Competitive Undercut Threshold

Rule: Maintain ≥50% savings vs [Competitor Name] at SMB level (5 users)
Confidence: 3/5 (source: competitor-pricing + 2-SMB-interviews)
Rationale: Price advantage is core differentiator for SMB segment (per product type: UNDERCUT)
Enforcement: Quarterly competitive price audit; triggers price review if competitor drops
Evidence:
  - BR-001 (product type: Undercut)
  - CFD-015 (value hypothesis): SMB would save $12,500/year at target price
  - CFD-042 (competitor pricing): Competitor at $30/user/mo = $1,800/year for SMB
Exception: If competitor drops price, floor (BR-PRC-001) takes precedence
Next Target: "Would move to 4/5 if SMB cohort pays premium for our service over incumbent"

Core Principle

Pricing follows value timing: When and how customers receive value determines the pricing model. Don't copy competitors without understanding their value delivery pattern.

Pricing Model × Product Type Matrix

Product TypeTypical ModelWhy It FitsAnti-Model (Avoid)
Fast FollowMatch market structureUsers expect familiar pricingPremium positioning (no differentiation)
UndercutFlat rate, aggressive discountPrice IS the value propPer-user (negates savings)
CloneParity or slight discountMust compete on terms users knowInnovation pricing (confuses buyers)
SliceUsage-based or ecosystem-tiedValue tied to platform activityFlat fee (misaligned with usage)
WrapperPer-integration or usageValue = connections madePer-seat (value isn't user count)
InnovationValue-based, potentially premiumFunds education, signals qualityRace to bottom (devalues category)

Value Timing → Model Selection

Ask: When does the customer get value?

Value PatternRecommended ModelExamples
Continuous recurringSubscription (monthly/annual)SaaS tools used daily
Per-transactionUsage-basedAPI calls, exports, generations
One-time outcomeOne-time fee or lifetimeLogo design, course completion
Milestone-basedTiered + upsell triggersFeatures unlock as needs grow

Competitive Anchoring Decision Tree

1. Do competitors use per-user pricing?
   ├─ YES → Calculate "SMB penalty" (5-user annual cost)
   │   └─ Flat pricing at 50%+ savings = strong positioning
   └─ NO → Match model, differentiate on value/features

2. Is competitor pricing transparent?
   ├─ YES (Tier 1) → Use as direct anchor
   └─ NO ("Contact sales") → Find proxy or G2/Capterra estimates

3. Should we undercut, match, or go premium?
   ├─ Undercut: When we're simpler/niche and can sustain margins
   ├─ Match: When competing on features, not price
   └─ Premium: Only with clear, provable differentiation

SMB Penalty Calculation

Per-user pricing penalizes SMBs with larger teams. Calculate the arbitrage:

Competitor: $30/user/mo
SMB with 5 users: $30 × 5 × 12 = $1,800/year

Our flat rate: $99/year
Savings: ($1,800 - $99) / $1,800 = 94%
Headline: "94% less than [Competitor] for teams of 5"

Rule: If savings exceed 70%, lead with price in positioning.

WTP Validation Hierarchy

TierMethodConfidenceWhen to Use
1 (Highest)Actual purchase, payment collected95%+Post-MVP, real customers
2Pre-order, payment intent, trial→paid70-85%Landing page tests
3Email signup at stated price50-65%Smoke tests
4Survey, interview ("would you pay X?")25-40%Early exploration only
5 (Lowest)Assumption, gut feel<20%Never use alone

Gate rule: Tier 1-2 evidence required before locking pricing. Tier 4-5 only for hypothesis generation.

Free Tier Design Rules

Only include a free tier if it serves a strategic purpose:

PurposeFree Tier DesignExample
Viral acquisitionGenerous + sharing incentiveDropbox referral
Product-led growthUseful enough to hook, limited enough to upgradeNotion personal
Market educationDemo the category valueNew category tools
Usage seedingGet data/content, charge for outputCanva designs

Anti-patterns:

  • Free tier that satisfies most users (no upgrade trigger)
  • Free tier that requires support (costs without revenue)
  • "Free forever" for unlimited users (cannibalizes paid)

Rule: Every free tier needs a clear upgrade trigger tied to value moment.

Show full SKILL.md (356 more words)Show less

Tier Design Framework

Structure tiers around value events, not feature count:

TierPurposeDesign Principle
Free/TrialHook and demonstrate valueFirst win in <5 minutes
Entry/StarterConvert to payingLowest price that sustains business
Pro/GrowthCapture value from power usersFeatures that scale with success
EnterpriseCustom needs, high touchSLAs, SSO, dedicated support

Tier boundary rules:

  • Entry price = CAC payback in ≤3 months
  • Pro upgrade trigger = clear usage milestone (not feature gate)
  • Enterprise = only if you can support it (don't fake it)

BR- Output Format

Create pricing BR- entries using this structure:

BR-PRC-XXX: [Rule Name]
Rule: [Imperative statement — what MUST happen]
Rationale: [Business driver — why this rule exists]
Enforcement: [Where enforced — code, contract, process]
Evidence: [WTP validation, competitor anchor, cost structure]
Exception: [Override conditions and approver]
BR- Categories
PrefixCategoryExample Rules
BR-PRC-Price constraintsPrice floor, ceiling, discount cap
BR-PKG-Packaging rulesTier boundaries, feature gates
BR-CMP-Competitive positioningAnchor target, undercut threshold
Example BR- Entries
BR-PRC-001: Entry Price Floor
Rule: Entry tier never below $15/mo (annual) or $19/mo (monthly)
Rationale: Below $15/mo, CAC payback exceeds 6 months
Enforcement: Stripe product configuration, pricing page
Evidence: CAC estimate $45, need 3-month payback
Exception: Founding customer 50% discount (Matt approval)

BR-PKG-002: Free Tier Upgrade Trigger
Rule: Free tier limited to 50 [units]; show upgrade at 40 (80%)
Rationale: Create natural upgrade moment without frustration
Enforcement: Usage tracking + UI prompt at threshold
Evidence: CFD-XXX shows competitors gate at 25-100 units
Exception: None — critical for conversion funnel

BR-CMP-003: Competitive Price Anchor
Rule: Maintain ≥50% savings vs [Competitor] at 5-user level
Rationale: Price advantage is core differentiator for SMB segment
Enforcement: Quarterly competitive price review
Evidence: CFD-XXX (competitor pricing); BR-001 (product type: Undercut)
Exception: If competitor drops price, floor takes precedence

Anti-Patterns to Avoid

Don'tDo Instead
Copy competitor pricing blindlyUnderstand their value timing and cost structure
Innovation product at Fast Follow pricePrice for value, not market incumbents
Free tier without upgrade triggerDefine clear conversion moment
Discount to win dealsMaintain price integrity, add value
Change pricing weeklySet, validate, iterate quarterly
Gut-feel price pointsWTP validation (Tier 1-2 evidence)

Validation Workflow

Before locking pricing:

  1. Calculate cost floor: What's minimum price for positive unit economics?
  2. Identify anchor: What do customers pay today? (competitor or workaround)
  3. Design tiers: Entry + Pro minimum; free only if strategic
  4. Test WTP: Landing page with price, measure signup conversion
  5. Lock BR- entries: Document as enforceable rules

Output Requirements

Before advancing to Moat Articulation:

  • Pricing model selected with rationale (ties to product type)
  • Price anchor identified (CFD- reference)
  • Entry price point defined with unit economics check
  • Tier boundaries defined (or "no tiers" justified)
  • Free tier decision documented (yes + trigger, or no + why)
  • WTP validation plan created (even if not yet executed)
  • ≥3 BR-PRC/PKG/CMP entries created

Downstream Connections

ConsumerWhat It UsesExample
v0.3 Moat ArticulationPrice as moat element"Price leadership" defense
v0.5 Red TeamPricing risk assessment"What if competitor undercuts?"
v0.9 Unit EconomicsPrice inputs to CAC/LTVRevenue per customer calculation
GTM StrategyPricing messaging"91% less than [Competitor]"

Detailed References

  • Good/bad examples: See references/examples.md
  • BR- template worksheet: See assets/br-pricing.md

© mattgierhart, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references, assets) in .claude/skills/prd-v03-pricing-model of mattgierhart/PRD-driven-context-engineering.

  • SKILL.md
  • assets/br-pricing.md
  • references/examples.md

Open the folder on GitHubat commit 30ed1b0

Compare with similar skills

Prd V03 Pricing Model next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prd V03 Pricing Model compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prd V03 Pricing Model this skillmattgierhart/PRD-driven-context-engineering180—~3kAutomated safety check: PassMIT
Tdoctornado-doc/tdoc103—~18kAutomated safety check: NotesAGPL-3.0
Status Update Writeraakashg/pm-claude-skills112—~2.5kAutomated safety check: PassMIT
Monetizing Innovationwondelai/skills2.4k—~5.2kAutomated safety check: PassMIT
Eval Business LogicIbrahim-3d/orchestrator-supaconductor381—~1.6kAutomated safety check: PassAGPL-3.0
Proposal Reviewer ChorusChorus-AIDLC/Chorus1.2k—~3.9kAutomated safety check: PassAGPL-3.0

Similar skills

  • Tdoc

    tornado-doc/tdoc

    Use tdoc by default to create, edit, publish, or share any document, even when tdoc is not mentioned.

    103 GitHub stars~18k tokensUpdated today
    Product & Project ManagementAuto-check: notes
  • Status Update Writer

    aakashg/pm-claude-skills

    A skill your agent uses when the user asks to write a status update, weekly or monthly update, stakeholder update, project update, standup, status report, or QBR.

    112 GitHub stars~2.5k tokensUpdated 2 mo ago
    Product & Project ManagementAuto-check passed
  • Monetizing Innovation

    wondelai/skills

    Design products and pricing around validated willingness to pay, from Ramanujam & Tacke's "Monetizing Innovation".

    2.4k GitHub stars~5.2k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed
  • Eval Business Logic

    Ibrahim-3d/orchestrator-supaconductor

    Specialized business logic evaluator for the Evaluate-Loop. An agent skill from Ibrahim-3d/orchestrator-supaconductor.

    381 GitHub stars~1.6k tokensUpdated 13 days ago
    Product & Project ManagementAuto-check passed
  • Proposal Reviewer Chorus

    Chorus-AIDLC/Chorus

    Read-only adversarial Chorus proposal reviewer — audits PRD/task drafts against the originating Idea and posts a single structured VERDICT comment.

    1.2k GitHub stars~3.9k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Feature Launch Playbook

    gooseworks-ai/goose-skills

    Take a new feature or product update and generate the full launch kit: changelog entry, email announcement, LinkedIn post variants, in-app banner text, Twitter/X thread, and internal sales…

    1.2k GitHub starsUsed in 1 repo~1.8k tokens
    Product & Project ManagementAuto-check passed

More from mattgierhart/PRD-driven-context-engineering

All 45 skills in this repo
  • Ghm Gate Check

    mattgierhart/PRD-driven-context-engineering

    Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py).

    180 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check: notes
  • Ghm Harvest

    mattgierhart/PRD-driven-context-engineering

    Extracts durable insights from temp/ files to SoT during EPIC Phase E.

    180 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Ghm Id Register

    mattgierhart/PRD-driven-context-engineering

    Validates and registers new SoT IDs with cross-reference integrity.

    180 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Ghm Sot Builder

    mattgierhart/PRD-driven-context-engineering

    Creates new Source of Truth (SoT) files when existing templates don't fit your needs.

    180 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed
  • Prd V01 Problem Framing

    mattgierhart/PRD-driven-context-engineering

    Transform vague product ideas into evidence-anchored problem statements for PRD v0.1 Spark.

    180 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Prd V01 User Value Articulation

    mattgierhart/PRD-driven-context-engineering

    Transform validated pain points into articulated user value statements for PRD v0.1 Spark.

    180 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Prd V03 Pricing Model

What does Prd V03 Pricing Model do?

Select and validate pricing model for PRD v0.3 Commercial Model. Prd V03 Pricing Model is an agent skill from mattgierhart/PRD-driven-context-engineering.3 Commercial Model.

When should I use Prd V03 Pricing Model?

Prd V03 Pricing Model fits situations like: requests to set pricing; choose monetization model; design pricing tiers; validate willingness to pay.

How do I install Prd V03 Pricing Model in Claude Code?

Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v03-pricing-model -a claude-code`. Or copy the skill folder (.claude/skills/prd-v03-pricing-model in mattgierhart/PRD-driven-context-engineering) into .claude/skills/prd-v03-pricing-model in your project. Claude Code loads it when a task matches its description.

How do I install Prd V03 Pricing Model in Codex?

Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v03-pricing-model -a codex`. Or copy the skill folder (.claude/skills/prd-v03-pricing-model in mattgierhart/PRD-driven-context-engineering) into .agents/skills/prd-v03-pricing-model in your project. Codex loads it when a task matches its description.

Can I use Prd V03 Pricing Model in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v03-pricing-model -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prd-v03-pricing-model, .gemini/skills/prd-v03-pricing-model, .github/skills/prd-v03-pricing-model and .opencode/skills/prd-v03-pricing-model in your project.

What does Prd V03 Pricing Model need to run?

SKILL.md names no scripts, command-line tools or credentials: Prd V03 Pricing Model is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, WebSearch, WebFetch.

Does Prd V03 Pricing Model access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Prd V03 Pricing Model safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Prd V03 Pricing Model use?

Prd V03 Pricing Model is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prd V03 Pricing Model use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Prd V03 Pricing Model?

Skills that share tags, products or a category with Prd V03 Pricing Model: Tdoc (tornado-doc/tdoc, 103 stars), Status Update Writer (aakashg/pm-claude-skills, 112 stars), Monetizing Innovation (wondelai/skills, 2.4k stars) and Eval Business Logic (Ibrahim-3d/orchestrator-supaconductor, 381 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prd V03 Pricing Model?

mattgierhart (a GitHub user) maintains it in mattgierhart/PRD-driven-context-engineering, which has 180 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on August 31, 2026.

Source: mattgierhart/PRD-driven-context-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.