@ssheleg/make-skill 0.21.0 → 0.23.0

package/CHANGELOG.md

@@ -1,5 +1,69 @@
 # Changelog
 
+## v0.23.0 — 2026-08-20 — the ledger said unshipped over the release commit
+
+The newest ledger section read *"Unshipped … no release cut"* and *"npm is still 0.21.0"*
+while HEAD **was** the v0.22.0 release commit and the registry served 0.22.0. Re-run against
+the artifact rather than re-graded, and `check_the_ledger_matches_what_shipped` now refuses
+the state: four plants, each watched at exit 1. It refused the row documenting itself once,
+because only `*"…"*` counts as a citation to it — which is now stated where the pattern
+lives rather than learned by whoever trips on it next.
+
+**The pile figure was a sample presented as a state.** MS-01 recorded *"1888 abandoned
+directories, 47.3 MB … unchanged by anything this repository ran after the fix"*. Recounted:
+**2688 directories, 83.6 MB** — and split at the fix's own commit time, which is the part
+that matters: **0** `planted/` and **0** `repo/` trees created after it, against **784 of
+2592** plant-guard trees. So the scoped claim holds, now by timestamp rather than by two
+samples taken a minute apart, and the total carries its measurement date.
+
+**The referral is discharged rather than claimed.** MS-01 left three sibling repositories
+shipping the identical leaking fixture. All three fixed it while this ran — the umbrella at
+`b371301`, `seo-aeo-audit` at `c859cba`, `agent-stack` porting `test/residue.py` from here —
+and `grep -c 'tempfile.mkdtemp()'` is now 0 in all four. Recorded as observed, not as work
+this release did.
+
+**Left open, and it is the honest kind.** `residue.report()` sees only what `workspace()`
+handed out, so a re-introduced bare `mkdtemp` prints *left nothing* over a live leak. That
+was watched happening in `agent-stack` before its port. The closing mechanism exists there;
+REQ-025 sits at `never` until it comes back here.
+
+
+## v0.22.0 — the gate left 47 MB in $TMPDIR and never said what it left
+
+**Two suites copied the tree to plant defects into it and never removed the copy.** The
+conformance audit named one; the sweep found the other, and it was the larger half by two
+orders of magnitude. Measured on this machine at the time of the fix: **1904 abandoned
+mkdtemp roots, 47.3 MB** — 60 planted skill dirs and 36 repo copytrees unambiguously this
+repository's, and 1808 plant-guard trees ambiguous, because four family repos ship the
+byte-identical fixture at the same line and nothing in the content distinguishes them.
+
+### `test/residue.py`
+
+A shared ledger in this repo's `plant_guard.py` idiom: `workspace()` hands out a
+`make-skill-test-` prefixed mkdtemp, `open_case` / `close_case` bind each tree to a case,
+and `report()` — wired to `atexit`, so no exit path skips it — removes what may go, keeps
+what a failure needs, and **prints one line either way**. A clean run says
+`residue: this run left nothing — N temp tree(s) created, N removed`, because the
+requirement is that completion *records* residue, not merely that there is none. A leak is
+then visible the first time the line changes.
+
+**The failure path keeps its tree, by decision and stated in three places.** A planted
+defect here is debugged by reading the copy the plant landed in, and a cleanup that runs
+only on the pass path removes the evidence exactly when you want it. The report names the
+kept path, its owning case, and the `rm -rf` that ends it — a kept tree with no stated
+remedy is a leak with better manners. A tree that refuses to delete is counted as **kept**,
+never as removed: the report does not claim a teardown it did not achieve.
+
+`test/residue_test.py` joins the gate with 8 cases, including the one that matters — stash
+the two fixes and it exits 1 naming both suites, then prints
+`residue: 2 of 2 temp tree(s) KEPT` with both paths. The failure path demonstrating itself.
+
+### Not swept
+
+The 1904 pre-existing directories were **left in place** and reported. Ownership of 1808
+of them cannot be established from their contents, and deleting state you cannot prove is
+yours is the one thing this kind of cleanup must not do.
+
 ## v0.21.0 — a gate's self-test runs in both directions
 
 *"A validator that can't fail is decoration"* has been the rule here since the standard was

package/README.md

@@ -261,10 +261,13 @@ plugins/make-skill/
 cursor/rules/make-skill.mdc           # self-contained Cursor rule
 bin/make-skill.js + package.json      # zero-dep npx installer
 test/validate.py                      # structural validator
+test/{plant_guard,checker_parity,residue}_test.py   # the gate's three suites
+test/{plant_guard,residue}.py         # did the plant land · what did the run leave
 test/evals/                           # trigger set + behavioral scenarios (data)
 .github/workflows/{validate,release}.yml
 install.sh  README.md  CHANGELOG.md  CONTRIBUTING.md  SECURITY.md  SKILL-CARD.md  LICENSE
 docs/evidence/{specs,plans}/       # historical design records
+docs/evidence/{backlog,verification}.md   # what is owed · what confirmed what
 ```
 
 ## Contributing

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ssheleg/make-skill",
-  "version": "0.21.0",
+  "version": "0.23.0",
   "description": "Create, retrofit, audit, and ship agent skills & Claude Code plugins the proven ssheleg way — conformance to the Agent Skills open standard AND Anthropic's platform rules (front-matter limits, disclosure budgets, per-surface runtime limits, the Skills API, evals) plus the Claude Code plugin reference (manifest schemas, component layout, claude plugin validate --strict), marketplace repo layout, version sync, validator + CI, multi-channel distribution (plugin, vercel skills CLI, npx, Cursor), npm gotchas, the review checklist for third-party skills, and MCP / A2A rules for protocol-connected skills. This package is the installer CLI.",
   "keywords": [
     "skill",
@@ -45,6 +45,6 @@
     "node": ">=16"
   },
   "scripts": {
-    "test": "python3 test/validate.py && python3 test/plant_guard_test.py && python3 test/checker_parity_test.py"
+    "test": "python3 test/validate.py && python3 test/plant_guard_test.py && python3 test/checker_parity_test.py && python3 test/residue_test.py"
   }
 }

package/plugins/make-skill/.claude-plugin/plugin.json

@@ -3,7 +3,7 @@
   "name": "make-skill",
   "displayName": "Make Skill",
   "description": "Create, retrofit, audit, and ship agent skills & Claude Code plugins the proven ssheleg way: conformance to the Agent Skills open standard, Anthropic's platform rules (surfaces, Skills API, evals) and the Claude Code plugin reference, marketplace repo layout, version sync, validator + CI, multi-channel distribution (plugin, vercel skills CLI, npx, Cursor), npm gotchas, end-to-end first publish, the review checklist for third-party skills, plus MCP / A2A references for protocol-connected skills.",
-  "version": "0.21.0",
+  "version": "0.23.0",
   "author": {
     "name": "ssheleg",
     "url": "https://x.com/sshlg93"

package/plugins/make-skill/skills/make-skill/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 compatibility: Authoring works on any agent. The bundled scripts/ need python3. Publishing steps need git, gh, node and npm; the plugin gates need the claude CLI. Not usable on the Claude API surface, which has no network and no runtime package install.
 metadata:
   author: ssheleg
-  version: "0.21.0"
+  version: "0.23.0"
   homepage: https://github.com/ssheleg/make-skill
 ---