sverklo 0.29.1 → 0.29.2

package/README.md

@@ -12,18 +12,22 @@ Sverklo gives coding agents repo memory: symbols, callers, diffs, blast radius,
 
 **Local-first** ◦ MIT ◦ no API keys ◦ no code upload ◦ first run downloads a local ONNX model
 
-Use grep when you know the exact string. Use Sverklo when the agent needs relationships: who calls this, what depends on it, what changed, and which project decisions still apply. The public bench covers 180 hand-verified tasks across 6 OSS codebases; the methodology and ground truth live in [sverklo/sverklo-bench](https://github.com/sverklo/sverklo-bench). [Bench](https://sverklo.com/bench/) · [paper](https://doi.org/10.5281/zenodo.19802051) · [90-second demo](https://www.youtube.com/watch?v=OX7aEgdlqhQ)
+**Use Sverklo when** your agent needs relationships before editing: callers, dependencies, tests, diff risk, or prior repo decisions.
+
+**Use grep/ripgrep when** you know the exact string, the repo is tiny, or the change is one file.
+
+Start with the no-write proof command before installing MCP config. The public bench covers 180 hand-verified tasks across 6 OSS codebases; the methodology and ground truth live in [sverklo/sverklo-bench](https://github.com/sverklo/sverklo-bench). [Bench](https://sverklo.com/bench/) · [paper](https://doi.org/10.5281/zenodo.19802051) · [90-second demo](https://www.youtube.com/watch?v=OX7aEgdlqhQ)
 
 ```bash
 cd your-project
-npm exec --yes --package=sverklo@latest -- sverklo prove --no-write --guided
+npm exec --yes --package=sverklo@latest -- sverklo prove --no-write --guided --markdown
 sverklo init --dry-run
 npm install -g sverklo && sverklo init
 ```
 
-`sverklo prove --no-write --guided` shows central files, a real symbol with callers, why that proof was selected, and the exact prompt to paste into your agent before any MCP config or instruction files are written. It may cache the local model/index under `~/.sverklo`, but it does not mutate your project. `sverklo init --dry-run` then previews the files `init` would touch; `sverklo init` writes the MCP config for your agent, appends local instructions to `AGENTS.md` or `CLAUDE.md`, and runs `sverklo doctor` to verify the handshake. Your code stays on your machine.
+`sverklo prove --no-write --guided --markdown` shows central files, a real symbol with callers, why that proof was selected, the exact prompt to paste into your agent, and a small feedback template before any MCP config or instruction files are written. It may cache the local model/index under `~/.sverklo`, but it does not mutate your project. `sverklo init --dry-run` then previews the files `init` would touch; `sverklo init` writes the MCP config for your agent, appends local instructions to `AGENTS.md` or `CLAUDE.md`, and runs `sverklo doctor` to verify the handshake. Your code stays on your machine.
 
-Need something shareable? Run `sverklo prove --markdown` to print a GitHub/Discord-ready proof receipt from your repo, then [post it in the proof thread](https://github.com/sverklo/sverklo/discussions/79).
+Need something shareable? Run `sverklo prove --no-write --guided --markdown` to print a GitHub/Discord-ready proof receipt from your repo, then [post it in the proof thread](https://github.com/sverklo/sverklo/discussions/79).
 
 Need local launch planning for the Sverklo account? `sverklo marketing` runs a local-first Twitter/X agent-team workflow from operator-provided snapshots. It ranks opportunities, drafts seed-content queues, checks profile health, and records human decisions without posting, scraping, replying, liking, reposting, following, or changing the profile.
 
@@ -42,7 +46,7 @@ Need local launch planning for the Sverklo account? `sverklo marketing` runs a l
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.19802051.svg)](https://doi.org/10.5281/zenodo.19802051)
 [![GitHub stars](https://img.shields.io/github/stars/sverklo/sverklo?style=social)](https://github.com/sverklo/sverklo/stargazers)
 
-> If `sverklo prove` surfaces useful repo context, please star the repo. It is the fastest way to help other agent-heavy teams find it.
+> If `sverklo prove` surfaces useful repo context, please post a receipt, correction, grep-better case, or setup-friction report in [the proof thread](https://github.com/sverklo/sverklo/discussions/79). If it helped, starring the repo also helps other agent-heavy teams find it.
 
 ![Sverklo bench:primitives token comparison](./docs/hero-token-comparison.png)
 
@@ -177,7 +181,7 @@ If the answer to your question is "exact string X exists somewhere," grep wins.
 | Tool | What it does |
 |------|-------------|
 | `search` | Hybrid BM25 + vector + PageRank search. Find code without knowing the literal string. |
-| `refs` | All references to a symbol, with caller context. Proves dead code with certainty. |
+| `refs` | All references to a symbol, with caller context. Flags likely dead-code candidates from the current reference graph. |
 | `impact` | Walk the symbol graph, return ranked transitive callers — the real blast radius. |
 | `review_diff` | Risk-scored review of `git diff`: touched-symbol importance x coverage x churn. |
 

package/dist/bin/sverklo.js

@@ -94,7 +94,7 @@ if (command && command !== "--help" && command !== "-h") {
         const HELP_BLURBS = {
             init: "Set up sverklo in your project (.mcp.json + CLAUDE.md, auto-detects Claude Code/Cursor/Windsurf/Antigravity). With --global: one-time-per-machine setup — write SVERKLO_SNIPPET to ~/.claude/CLAUDE.md and ~/.codex/AGENTS.md, register the project, gitignore .sverklo/, import memories. Skips per-project boilerplate.",
             doctor: "Diagnose MCP setup issues. Run after `init` to verify the agent can reach sverklo.",
-            prove: "Show a first-run repo-memory proof: central files, a real symbol with callers, and a paste-ready agent prompt. Flags: --markdown, --receipt, --format text|markdown.",
+            prove: "Show a first-run repo-memory proof: central files, a real symbol with callers, and a paste-ready agent prompt. Flags: --no-write, --guided, --markdown, --receipt, --format text|markdown.",
             audit: "Run codebase audit and emit a graded report. Flags: --format markdown|html|json|graph|arch|obsidian, --output PATH, --open, --badge, --publish.",
             "audit-diff": "Incremental architectural quality gate. Audits `git diff` for new cycles + fan-in spikes. Flags: --against REF, --fan-in-threshold N, --format human|json, --show-existing, --verbose. Exits 1 on regression.",
             review: "Risk-scored diff review (CI-friendly). Flags: --ref REF, --ci, --format markdown|json, --max-files N, --fail-on low|medium|high.",