diff --git a/plugins/autonomy/.claude-plugin/plugin.json b/plugins/autonomy/.claude-plugin/plugin.json
index 0eaa2b8fc..18c0a833b 100644
--- a/plugins/autonomy/.claude-plugin/plugin.json
+++ b/plugins/autonomy/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "autonomy",
-  "version": "0.12.1",
+  "version": "0.12.2",
   "description": "Governed autonomous agent operation: role-topology, binding-seam, wiring-vs-advisor, telemetry, return-accounting, trigger-dispatch, per-work-class guardrail-matrix, standing-routine-catalog, and design-only runner-charter contracts for climbing the AI-adoption ladder, plus a guided-setup skill that discovers an adopting org's state, writes its schema-versioned binding, wires standards-pinned OTLP emission with a zero-cost file-artifact default, wires human-attested return capture at the task boundary, wires signal adapters with one governed dispatch entrypoint, binds the five-class guardrail matrix to an org's isolation substrates with an in-boundary live-validation probe before recording each fail-closed binding, and stands up standing-routine-catalog classes as scheduled temporal signal adapters behind the one governed queue with free scheduling defaults wired as reviewable changes and each routine's work-class mapping homed on the security surface.",
   "author": {
     "name": "Melodic Software",
diff --git a/plugins/autonomy/CHANGELOG.md b/plugins/autonomy/CHANGELOG.md
index 8abd6f4d0..ab9300578 100644
--- a/plugins/autonomy/CHANGELOG.md
+++ b/plugins/autonomy/CHANGELOG.md
@@ -6,6 +6,20 @@ All notable changes to the `autonomy` plugin are documented here. Format follows
 Versions 0.1.0–0.7.0 predate this file (introduced with 0.7.1); their history lives in the
 merged work-package PRs (#333, #343, #356, #372, #377, #600, #676).
 
+## [0.12.2]
+
+### Fixed
+
+- **`reference/routines.md`: the `goal` glossary row no longer claims a budget cap ends the
+  session.** The row read "until a separate grader judges the condition met or a budget cap trips";
+  the official page documents a closed two-item set — "A goal keeps running until the condition is
+  met or you run `/goal clear`" — and its own section on bounding a goal's duration offers a turn or
+  time clause inside the condition, not a spend cap. The only dollar cap Claude Code's CLI documents
+  is the `--max-budget-usd` flag, which is print-mode-only and invocation-scoped, whereas this row
+  is `session-scoped`; a cap-stopped invocation also leaves the goal neither achieved nor cleared,
+  so it is restored on `--resume`/`--continue` — the cap ends the process while the goal outlives
+  it. The replacement clause names the second of the two events that actually change goal state.
+
 ## [0.12.1]
 
 ### Changed
diff --git a/plugins/autonomy/reference/routines.md b/plugins/autonomy/reference/routines.md
index 449ae9d24..ac35c1a4f 100644
--- a/plugins/autonomy/reference/routines.md
+++ b/plugins/autonomy/reference/routines.md
@@ -45,7 +45,7 @@ fire fresh ones.
 | Term | Family | Meaning |
 |---|---|---|
 | `loop` | session-scoped | repetition on an interval inside one session; dies with the session |
-| `goal` | session-scoped | completion condition — the session keeps going until a separate grader judges the condition met or a budget cap trips |
+| `goal` | session-scoped | completion condition — the session keeps going until a separate grader judges the condition met or the goal is cleared |
 | `batch` | session-scoped | parallel fan-out over decomposed units of one brief; NOT bulk-inference batch APIs (a corrected research conflation) |
 | `dynamic workflow` | session-scoped | orchestration whose decomposition and sub-steps the session composes at run time; ends with the session |
 | `schedule` | standing | the standing time trigger |