Launch Tier Classification

Every release gets classified before planning begins. Source: Lauchengco (Loved).

Preflight: Read target canvas file(s) before any Write/Edit

Hard rule. Before issuing Write or Edit against any .claude/canvas/*.yml, use the Read tool on that file in this session. Claude Code's Read-before-Write check requires the Read tool specifically — cat/head/grep via Bash do NOT satisfy it.

Edit vs Write — different cost profiles (verified 2026-05-14):

• Edit (exact-string replacement): Read with limit: 1 satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent Edit calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., purpose.yml at 800+ lines).
• Write (full replacement): do a full Read first. Write obliterates the file; you should see what you're about to replace. The limit:1 shortcut is not appropriate here.

ID-bearing entries — scan the ID space before assigning (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:

grep "^  - id: <prefix>-" .claude/canvas/<file>.yml | sort -u

Replace <prefix> with the canvas's ID prefix (comp for landscape, opp for opportunities, sol for solutions, ht for human-tasks, etc.). Then pick the next free integer. validate_canvas.py has a duplicate-ID check (lines 230-239) that catches the failure on CI, but a duplicate can persist in the working tree for days if CI isn't run between edit and discovery — see roadmap-repo corrections.md 2026-05-15 "Duplicate canvas ID created in landscape.yml" for the worked example.

Original failure mode: anti-pattern #7 instance #5, 2026-05-09 — agent conflated Bash head with the Read tool, lost ~14k tokens to a Write-fail → remedial-full-Read → re-Write loop. The limit:1 discipline (graduated 2026-05-14, v0.23.18) prevents the second-order cost where the agent correctly follows the rule but full-Reads every time. The ID-scan discipline (graduated 2026-05-15, v0.23.19) prevents the related class where the agent reads enough of the file to satisfy the Edit check but not enough to see existing ID assignments — kin to anti-pattern #8 (Stale State Read).

If this skill writes to multiple canvas files, register each one first (limit:1 for Edit-only paths; full Read for Write paths) AND ID-scan any prefix you intend to assign.

See CLAUDE.md Canvas writes — Read before Write for the canonical rule.

Tier Definitions

Classification Criteria

• Does this change our positioning? -> Tier 1
• Does this strengthen existing positioning? -> Tier 2
• Is this an incremental improvement? -> Tier 3

Per-Tier Activities

Software (default)

Tier 1: Press, events, campaigns, sales enablement, analyst briefings, customer advisory Tier 2: Blog post, targeted campaigns, sales enablement update, in-product announcement Tier 3: Release notes, changelog, in-product notification, knowledge base update

Content Products (courses, publications, media) (v0.11.0)

Tier 1: Platform launch (new course on marketplace), PR/media coverage, launch webinar, guest appearances Tier 2: New module/section, cross-promotion, community announcement, guest post Tier 3: Content update, errata fix, supplementary material, minor revision

AI Tools (v0.11.0)

Tier 1: Public launch, ProductHunt/HackerNews, documentation site, demo video Tier 2: New capability/model, integration partnership, case study Tier 3: Prompt improvement, model update, bug fix, eval result improvement

Service Offerings (v0.11.0)

Tier 1: New service line launch, case study PR, conference talk, partnership announcement Tier 2: New package/tier, testimonial campaign, process improvement announcement Tier 3: Pricing update, workflow refinement, expanded availability

Behavioral Science in Positioning (Shotton)

Use biases ETHICALLY to help users understand value:

• Social proof: Reference customers, usage numbers (real, not inflated)
• Anchoring: Frame value relative to alternatives
• Framing: Position the benefit, not just the feature
• Never: Confirmshaming, hidden costs, forced continuity, misdirection

Canvas Output

Update .claude/canvas/go-to-market.yml with tier classification and launch plan.

Ethical Engagement Design (Eyal -- Hook Model + Indistractable)

Eyal's work spans two complementary books: Hooked (2014) provides the Hook Model for building habit-forming products; Indistractable (2019) provides the user-side framework for managing attention. The Manipulation Matrix below bridges both — ethical engagement design means building hooks that users would choose even with full information.

The Hook Model is most relevant at L3 (Solution design) for engagement architecture, not just L5 (Market). Apply during solution design when the product requires recurring usage.

For products that need user retention, design engagement ethically using the Hook Canvas:

Hook Canvas

Map the four components of habit formation:

• Trigger: What prompts the user to engage? (External: notification, email. Internal: emotion, routine.)
• Action: What is the simplest behavior in anticipation of reward? (Must be easier than thinking.)
• Variable Reward: What reward satisfies the user's need while leaving them wanting more? (Tribe: social, Hunt: resources, Self: mastery.)
• Investment: What bit of work does the user put in that improves the next cycle? (Data, content, reputation, skill.)

Manipulation Matrix (Ethical Gate — NUDGE)

Before implementing engagement design, answer honestly:

1. Does it materially improve the user's life? (Not just "engagement" — actual value.)
2. Would you use it yourself? (The maker's test.)

Only Facilitator products should be built without reservation. Entertainers need honest self-assessment. Peddlers and Dealers trigger anti-pattern #10 (Dark Pattern Marketing).

Update .claude/canvas/go-to-market.yml engagement_design section with Hook Canvas results.

Source: Eyal (Hooked), with ethical framework from the Manipulation Matrix

Pre-Launch Bias Check

Before classifying a launch tier, run /mycelium:bias-check for L5-specific biases:

• Optimism bias: Are we overweighting positive signals and ignoring negative ones?
• Confirmation bias: Are we seeking validation that "it's ready to ship" rather than honestly assessing market readiness?
• Anchoring: Are we fixated on the initial positioning without considering what evidence now suggests?
• Sunk cost fallacy: Are we launching because we've invested too much to stop, not because the market signals are positive?

If /mycelium:bias-check reveals significant biases, address them before finalizing the launch tier.

After Launch: The L5 -> L2 Feedback Loop

This is critical. After launch, market feedback must flow back into discovery:

1. Capture market signals (within 2-4 weeks post-launch). Check the product-type-appropriate metrics canvas via /mycelium:dora-check:

   Software: feature usage, retention, conversion, support tickets, NPS/CSAT Content: refund rate, completion rate, drop-off points, return