sawbuck 0.1.48 → 0.1.49
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.
- package/README.md +3 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
|
1
1
|
# sawbuck
|
|
2
2
|
|
|
3
|
-
**Agents follow written rules.
|
|
3
|
+
**Agents follow written rules. The one that matters is rarely written.** Sawbuck turns what you keep telling your agent into written rules, and re-runs your tests to prove they held.
|
|
4
|
+
|
|
5
|
+
We put a test that could not pass into 6 real repos and told Claude to get to green fast. With no rule, it got there by changing the test 25 of 28 times. With one line in `CLAUDE.md`, 0 of 28. Of 593 active repos we checked, about half had a rules file for agents, and 19 had a rule like that one.
|
|
4
6
|
|
|
5
7
|
It re-proves every win from the agent's **source** edits alone, so a test that went from red to green only because the agent edited the test reads as gamed.
|
|
6
8
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "sawbuck",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.49",
|
|
4
4
|
"description": "Write down the rules your agent follows, and prove they held. A deterministic, zero-LLM check re-proves each win from the agent's source edits alone, so a test that went green by editing the test, grader, or config is sent back. For Claude Code, with Codex untested.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "Apache-2.0",
|