Pricing and cadence split Objective evenly — 0.2 of the total each.
Fewer than 3 votes on record → neutral 0.50, shown as provisional rather than as a real reading.
3 windows withheld for a thin sample — last 24 hours, last 7 days, last 30 days. Withheld, not averaged in as a zero.
Community discussion sentiment over 7d/30d at 0.6/0.4.
Editorial layer · not in the score
The Honest Stack is our own opinion about what to actually use. It is deliberately not an input to the v2market signal — there is no editor’s term in the formula, and no field in the data model that carries one. Read it as a second, human opinion beside the number, never as part of it.
Entered at catalog seed — pending verification.
Claude offers a free plan, a Pro plan for $20/month (or $17/month annually), and a Max plan starting from $100/month.
The digest · weekly
Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →
The most recent events linked to Claude Code, so you can read the record behind the number. These citations are context, not a score component — none of them is an input to the v2 formula above.
Show HN: Orate – On-device neural text-to-speech queue for Mac
Show HN: Tokenmaxx – CLI that merges usage across Claude Code and Codex accounts
Show HN: CodeAlmanac – Karpathy-style codebase wiki from your conversations
Daily net of anonymous better/same/worse votes. Bursts and over-cap votes are flagged automatically and excluded from every aggregate — they stay in the log, which is append-only.
No votes yet — cast the first one above.
Version v2.1.216 added a sandbox.filesystem.disabled setting and fixed multiple issues including slowdowns in long sessions, auto mode denying commands, and various session-related bugs.
Version v2.1.215 changed Claude so it no longer runs /verify and /code-review skills automatically, requiring explicit invocation.
Version v2.1.214 added the EndConversation tool, a periodic progress heartbeat, an ISO modified timestamp to memory file frontmatter, and OpenTelemetry log attributes, while fixing various permission check issues.
v2.1.212 changes `/fork` behavior, adds `claude auto-mode reset`, introduces session-wide limits on WebSearch tool calls and subagent spawns, and fixes several issues including plan mode auto-running file-modifying Bash commands.
A new flag and environment variable were added to include subagent text and thinking in stream-json output, and several fixes were implemented.
Screen reader mode, vim insert-mode remaps, corporate launcher wrapper support, and extensive fixes.
Subagents now run in the background by default; Claude in Chrome reaches GA; /dataviz skill added.
Sonnet 5 with native 1M-token context ships as the new default model.