v0.24.1 — the ledger catches up to the version it ships

.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "displayName": "Agent Stack",
       "source": "./plugins/agent-stack",
       "description": "Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent cards, the MCP Registry, and gateways; agent-harness — system prompts, tool shaping, workflow-vs-agent, and auditing an agent system.",
-      "version": "0.24.0",
+      "version": "0.24.1",
       "author": {
         "name": "ssheleg",
         "url": "https://x.com/sshlg93"

CHANGELOG.md

@@ -1,3 +1,13 @@
+## v0.24.1 — the ledger catches up to the version it ships
+
+A member's ledger is fixed in that member's own release. The umbrella's ratchet
+counts members whose ledger describes a version older than they ship, and the
+release wave of 2026-09-10 put this one on that list — its gate did not demand a
+section, the umbrella does.
+
+The v0.24.0 section is written now, naming what shipped and what
+confirmed it.
+
 ## 0.24.0 — the agent stack closes its audit findings
 
 Sherlock external-v3 (24 findings), each carrying its own executable regression

SKILL-CARD.md

@@ -5,7 +5,7 @@
 | Field | Value |
 |---|---|
 | Pack | `agent-stack` |
-| Version | `0.24.0` |
+| Version | `0.24.1` |
 | Skills | `agent-orchestrator`, `agent-evals`, `agent-interop`, `agent-harness` |
 | License | MIT |
 | Source | https://github.com/ssheleg/agent-stack |

docs/evidence/verification.md

@@ -10,6 +10,16 @@ This file exists because its absence read as zero exposure. `sshlg-skills` board
 
 ---
 
+## Shipped state — v0.24.0 (2026-09-10)
+
+Sherlock external-v3 (24 findings), each carrying its own executable regression.
+
+| REQ | What ships | How it was confirmed | Confirmed |
+|---|---|---|---|
+| SH-regressions | Every sherlock finding assigned here closes with an executable regression | `test/audit_regressions/` holds 23 suites; `npm test` runs all of them and exits 0 | **observed** |
+| SH-measure | The house skill audit MEASURES the token budget in CI rather than estimating it | the pinned auditor ran with no tokenizer and issued a token verdict from a chars/3.9 estimate, which gapped `agent-evals` (~4961) and `agent-orchestrator` (~4762) — both inside 4750 when measured (4374 and 4309). Pin moved to make-skill@5ca5c36 and the job installs tiktoken | **observed** — the estimate and the measurement disagreed on this repository, in CI |
+| Gate | The whole suite on this tree | `npm test` EXIT=0; `audit_skill.py --house` 0 GAP on all four skills | **observed** |
+
 ## Shipped state — v0.23.2 (2026-09-06)
 
 Measured on the release-candidate tree before the tag exists. Family audit wave

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ssheleg/agent-stack",
-  "version": "0.24.0",
+  "version": "0.24.1",
   "scripts": {
     "test": "python3 test/validate.py && python3 test/plant_guard_test.py && node test/installer_test.js && npm run test:audit",
     "test:audit": "for t in test/audit_regressions/*.py; do python3 \"$t\" || exit 1; done"

plugins/agent-stack/.claude-plugin/plugin.json

@@ -3,7 +3,7 @@
   "name": "agent-stack",
   "displayName": "Agent Stack",
   "description": "Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent cards, the MCP Registry, and gateways; agent-harness — system prompts, tool shaping, workflow-vs-agent, and auditing an agent system.",
-  "version": "0.24.0",
+  "version": "0.24.1",
   "author": {
     "name": "ssheleg",
     "url": "https://x.com/sshlg93"