@humanbased/crosscheck 0.16.0-beta.32 → 0.16.0-beta.34

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +39 -9
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -14,22 +14,52 @@
14
14
  <img src="./assets/screenshot-watch.png" alt="crosscheck watch — live pipeline view" width="860" />
15
15
  </p>
16
16
 
17
- **Stop merging AI slop. Crosscheck turns agent-written PRs into merge-ready patches with a configurable Review -> Fix -> Recheck pipeline.**
17
+ **Your agents ship fast. Crosscheck makes sure they ship right.**
18
18
 
19
- AI coding agents are fast, but they can still ship regressions, half-finished fixes, brittle edge cases, and "early victory" PRs that look done before they are solid. Crosscheck adds an independent safety loop: let one agent write the patch, let another review it, send the findings back to the author, then recheck the result before merge.
19
+ AI coding agents create PRs faster than review habits can absorb. The failure mode isn't broken builds — it's *early victory*: patches that pass CI, look complete, and still hide regressions, brittle edge cases, or half-finished fixes.
20
20
 
21
- Define the workflow in `workflow.yml`: review-only, review + fix, or the full review + fix + recheck cycle. Each step runs through the `claude` or `codex` CLI against your existing subscriptions — no API keys, no per-review cost.
21
+ Crosscheck adds an independent Review → Fix → Recheck loop. One agent writes the patch. Another reviews it. Findings go back to the author to repair. The result gets rechecked before merge. The PR moves toward genuinely merge-ready — not just "looks green."
22
22
 
23
- Built by [Humanbased](https://github.com/humanbased-ai) as a showcase of practical engineering craft for the agentic coding era.
23
+ No new hosted service. No per-review API bill. Crosscheck runs through the `claude` and `codex` CLIs you already have — your existing subscriptions, your machine or server.
24
24
 
25
- Read the field report: [What 295 Agentic PRs Taught Us About Code Review](https://blog.humanbased.ai/posts/agentic-pr-quality-crosscheck/). It explains why Humanbased built Crosscheck after analyzing 295 agentic PRs and retained Crosscheck logs from real internal workflow.
25
+ Built by [Humanbased](https://github.com/humanbased-ai). Read the field report: [What 295 Agentic PRs Taught Us About Code Review](https://blog.humanbased.ai/posts/agentic-pr-quality-crosscheck/) — 295 agentic PRs analyzed, real Crosscheck logs included.
26
26
 
27
27
  ## Why crosscheck?
28
28
 
29
- - **Combats AI slop before merge** — catches code regressions, incomplete fixes, hallucinated assumptions, and brittle "looks green" patches.
30
- - **Uses independent reviewers** — route Claude-authored PRs to Codex, Codex-authored PRs to Claude, or run a single-vendor loop when that is what you have.
31
- - **Closes the loop** — review findings can become a fix step and then a recheck step, so the PR moves toward real merge readiness instead of another comment thread.
32
- - **Runs on your machine or server** — no new hosted code review service, no per-review API bill, no extra infrastructure to trust.
29
+ **Agent velocity without lowering the merge bar.**
30
+
31
+ - **Independent eyes, not self-review** — route Claude-authored PRs to Codex and vice versa. Self-review is exactly where early-victory failures hide.
32
+ - **Review → Fix → Recheck, not just comments** — findings return to the author agent for repair; a clean recheck follows before merge. PRs move forward, not sideways.
33
+ - **No new vendor** — runs through the `claude` and `codex` CLIs you already pay for. No per-review bill, no extra trust surface.
34
+ - **Configurable for any team size** — review-only mode, review + fix, or the full loop. Personal laptop via `watch`, always-on server via `serve`, one-shot via `review`.
35
+
36
+ ## Who uses crosscheck
37
+
38
+ | Persona | Problem | How crosscheck helps |
39
+ |---|---|---|
40
+ | **Solo agentic builder** | Same agent that wrote the code may self-approve incomplete work | Independent reviewer from a different vendor, on your machine |
41
+ | **Technical founder** | AI PRs look done before delivering stable value | Closes the loop: review finding → agent fix → clean recheck |
42
+ | **Engineering lead** | Agent use is hard to supervise or standardize | Configurable workflow, review-only mode, and a visible PR audit trail |
43
+ | **OSS maintainer** | Review bandwidth is scarce; comments must be actionable | One-shot `crosscheck review` posts concrete findings directly on the PR |
44
+
45
+ ### Common workflows
46
+
47
+ ```bash
48
+ # Catch regressions before merging a solo PR
49
+ crosscheck run <pr-url>
50
+
51
+ # Continuous review on every incoming agent PR
52
+ crosscheck serve # always-on team server
53
+
54
+ # Review stale PRs from a queue
55
+ crosscheck scan && crosscheck kickass
56
+
57
+ # One-shot review of a specific PR
58
+ crosscheck review <pr-url>
59
+
60
+ # Loop until the agent produces an approved patch
61
+ crosscheck run <pr-url> --crazy
62
+ ```
33
63
 
34
64
  ---
35
65
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@humanbased/crosscheck",
3
- "version": "0.16.0-beta.32",
3
+ "version": "0.16.0-beta.34",
4
4
  "description": "AI code review pipeline that turns agent-written PRs into merge-ready patches",
5
5
  "bin": {
6
6
  "crosscheck": "dist/cli.js",