docs: add audience fit and social preview starter

CHANGELOG.md

@@ -5,7 +5,9 @@
 ### Repository positioning and metadata
 - Refreshed the README opening section to position Hermit as a distinct open-source executor layer for Claude Code and Codex rather than a generic terminal UI.
 - Added a comparison section that explains why teams would pair Hermit with Claude Code or Codex instead of treating it as a replacement orchestrator.
-- Added a reusable `docs/open-source-positioning.md` copy deck for repository descriptions, social preview messaging, and release framing.
+- Added explicit "who Hermit is for / not for" guidance so the landing page qualifies the intended audience instead of only describing features.
+- Added a reusable `docs/open-source-positioning.md` copy deck for repository descriptions, social preview messaging, release framing, and audience-fit guidance.
+- Added an editable `docs/assets/hermit-social-preview.svg` starter asset for repo cards, launch posts, and future GitHub social preview work.
 - Updated package and repository-facing descriptions to emphasize the MCP executor + cheaper execution lane story instead of the outdated Codex-first fallback wording.
 - Tightened the public metadata around predictable local / flat-rate defaults so the repository pitch matches the current install and routing policy.
 

README.md

@@ -39,6 +39,21 @@ Why Hermit stands out:
 
 Hermit is not trying to replace your orchestrator. It gives you a second lane: use the premium model for judgment, and use Hermit for the mechanical throughput that makes repositories expensive to operate at scale.
 
+## Who Hermit is for
+
+- Teams that already like Claude Code or Codex for planning, review, and decision-making, but want a cheaper execution lane for repo mechanics.
+- Developers who want MCP-driven follow-through on edits, tests, commits, and release chores without spending premium-model tokens on every step.
+- Repositories that need predictable default routing toward local or flat-rate models instead of surprising hosted fallback costs.
+- Maintainers who want one shared executor layer even if different contributors prefer different orchestrators.
+
+## Who Hermit is not for
+
+- People looking for a brand-new premium planner to replace Claude Code or Codex entirely.
+- Teams that want a single hosted model to do both judgment and execution with no planner/executor split.
+- Workflows where provider cost predictability, MCP task handoff, and execution-lane separation are not important.
+
+If your pain is not "my orchestrator is smart enough, but too much of its time is spent on repetitive repo labor," Hermit is probably not the right abstraction.
+
 ## Install
 
 ```bash
@@ -146,5 +161,6 @@ MIT — see [LICENSE](LICENSE).
 - [docs/hermit-variants.md](docs/hermit-variants.md) — the `-hermit` skill family
 - [docs/measure-savings.md](docs/measure-savings.md) — cost-savings measurement protocol
 - [docs/open-source-positioning.md](docs/open-source-positioning.md) — short public-facing copy for descriptions, releases, and future social previews
+- [docs/assets/hermit-social-preview.svg](docs/assets/hermit-social-preview.svg) — editable social-preview starter asset for repo cards and launch posts
 - [CHANGELOG.md](CHANGELOG.md) — notable release and policy changes
 - [benchmarks/](benchmarks/) — reproducible task specs and community datapoints

docs/open-source-positioning.md

@@ -17,6 +17,18 @@ Hermit adds a dedicated execution lane to your coding-agent stack. Keep Claude C
 - It defaults toward cost-predictable local or flat-rate models instead of surprising hosted fallback behavior.
 - It works across multiple orchestrators, which makes it easier to adopt as shared team infrastructure.
 
+## Audience fit
+
+### Great fit
+- Teams already invested in Claude Code or Codex that want a dedicated execution lane.
+- Repositories where test runs, refactors, commits, and release chores are burning expensive planner tokens.
+- Maintainers who want one MCP executor path shared across multiple orchestrators.
+
+### Weak fit
+- Users who want Hermit itself to be the premium planner.
+- Teams that are happy with one hosted model doing both judgment and execution.
+- Very small workflows where planner/executor separation adds more ceremony than value.
+
 ## Social preview copy ideas
 
 ### Option A
@@ -32,6 +44,26 @@ Claude Code or Codex plans.
 Hermit executes.
 Your bill stays predictable.
 
+## Homepage / hero copy variants
+
+### Variant A
+Keep the premium orchestrator for judgment.
+Use Hermit for the repetitive repo work.
+
+### Variant B
+Claude Code or Codex thinks.
+Hermit ships the mechanical follow-through.
+
+### Variant C
+One MCP executor layer.
+Cheaper execution across multiple orchestrators.
+
+## Social preview asset
+
+- Starter asset: `docs/assets/hermit-social-preview.svg`
+- Intended use: GitHub social preview image mockups, release cards, launch posts, and docs screenshots.
+- Design direction: dark terminal-like card, premium planner on top, cheaper execution lane underneath, no provider-specific billing claims beyond predictable local / flat-rate defaults.
+
 ## Release-note framing
 
 Hermit helps teams separate high-value reasoning from high-volume execution. That means better cost control, cleaner planner/executor boundaries, and an MCP-native path from idea to tested repo change.