Skip to content

Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.

docs(rigor): guides say a repeated cause can become a pending watch [I1]

Corey Olson2682e531e92a
diff --git a/docs/rigor.md b/docs/rigor.md
index 560fca0e..40d2e466 100644
--- a/docs/rigor.md
+++ b/docs/rigor.md
@@ -45,6 +45,8 @@ Drafting approves nothing. The person reviews each draft with its evidence and i
pullboard spec approve <ids> | decline <ids> --reason "why"
+A repeated cause that a check can watch is drafted as a pending board watch instead, citing its repeats and the proof. It appears in Needs you with the other drafts, and it runs only after the person approves it.
+
Once a doctrine row is approved, every submit runs the doctrine check, so the rule holds from then on. Check the current rules and their counts with:
pullboard doctrine check
diff --git a/docs/sentinels.md b/docs/sentinels.md
index 2dc70a02..fdaae28b 100644
--- a/docs/sentinels.md
+++ b/docs/sentinels.md
@@ -57,3 +57,5 @@ The owner hears about a watch only when its result changes. A red result sends "
### How Rigor uses a sentinel
Each red run counts as a failure with the cause `sentinel:<name>`. Two red runs of the same watch make a repeated cause, and Rigor lists it in `pullboard rigor`. From there it follows the same path as any other repeated cause, so the coordinator can draft a rule and the person decides on it. See [Rigor](rigor.md) for how that works.
+
+The path can also run the other way. When a repeated cause is one a check can watch, Rigor drafts it as a pending board watch, citing its repeats and the proof that the check fails and then passes. The person approves it from Needs you, the same way as any Rigor draft, and until then it does not run.