sshlg-skills 1.71.0 → 1.72.0

package/CHANGELOG.md

@@ -1,3 +1,15 @@
+## v1.72.0 (2026-10-20): task-pipeline 1.98.0, the proportional run
+
+- **Pin: task-pipeline 1.98.0.** A small change takes the short path by itself
+  (`scripts/short_path.py`); a run reads `SKILL.md` at entry and each reference on its
+  trigger (reading floor 236 KB to 35 KB on the short path); an R1 node certifies with one
+  verifier tier, a repeat round on an unchanged tree is refused and the ceiling parks the
+  node; the retro floor has a 12 KB budget (`scripts/retro_budget.py`), entries name a Class
+  and a Cost, and `learned.md` gains rules 33 to 39 from the 2026-10-20 survey of 54
+  retrospectives. Its three descriptions fell to 386-399 characters (B-154 closed).
+- **Ratchets:** family description total 17,601 to 16,103; the 500 reserve's tight count 17 to 14.
+- **Board:** B-242, a member installed in user plus local scopes is never upgraded.
+
 ## v1.71.0 (2026-10-20): ten members re-trimmed, the listing fits again
 
 - **Pins:** make-skill 0.33.0 (a description is a router: target 400, warning above 500,

package/README.md

@@ -47,7 +47,7 @@ scripts. No services, no telemetry, no API keys.
 | Skill | Version | What it does |
 |---|---|---|
 | **[super-ux](https://github.com/ssheleg/super-ux)** | 0.63.0 | Scenario-driven UI development. A versioned design chain in `docs/ux/` — the product vision → personas and jobs → user flows → a screens-and-states map with Figma frames → traced scenarios → evidence-backed audits → fix plans, plus `docs/brand/` for how the product speaks. One `/ux` entry point that reaches every skill, two doc-drift linters and a contract doctor. |
-| **[task-pipeline](https://github.com/ssheleg/task-pipeline)** | 1.97.1 | Full-cycle delivery orchestrator. An intake grill interrogates the request into a complete brief, then **ten gated stages** carry it — docs, brainstorm and decompose, spec, plan, build, tests, deploy, post-deploy, wiki, acceptance — refusing to advance until each gate passes. Documentation is a deliverable with its own portable gate, and the retrospective it leaves behind is traceable to the commit that earned each lesson. Ships `project-audit`: a cold-start audit of a whole project — discovery, probes whose unmet needs read `blind` rather than clean, production evidence including one artefact served under two channels, and an HTML report beside a JSON sidecar that says what moved. |
+| **[task-pipeline](https://github.com/ssheleg/task-pipeline)** | 1.98.0 | Full-cycle delivery orchestrator. An intake grill interrogates the request into a complete brief, then **ten gated stages** carry it — docs, brainstorm and decompose, spec, plan, build, tests, deploy, post-deploy, wiki, acceptance — refusing to advance until each gate passes. Documentation is a deliverable with its own portable gate, and the retrospective it leaves behind is traceable to the commit that earned each lesson. Ships `project-audit`: a cold-start audit of a whole project — discovery, probes whose unmet needs read `blind` rather than clean, production evidence including one artefact served under two channels, and an HTML report beside a JSON sidecar that says what moved. |
 | **[agent-sync](https://github.com/ssheleg/agent-sync)** | 1.23.0 | Several agents, one repository, no collisions. Leases with a TTL so two agents cannot claim the same work, race-free id reservation, a run journal and a generated board — over a pluggable knowledge cloud. The answer to "two sessions just committed over each other". |
 | **[make-skill](https://github.com/ssheleg/make-skill)** | 0.33.0 | A skill that builds skills. Create, retrofit, audit and publish agent skills and Claude Code plugins: conformance to the [Agent Skills](https://agentskills.io/specification) open standard, [Anthropic's platform rules](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) (per-surface runtime limits, the Skills API, evals) and the [Claude Code plugin reference](https://code.claude.com/docs/en/plugins-reference), marketplace layout, version sync, validator + CI, every distribution channel, the review checklist for third-party skills, and what a *skill author* must know about MCP and A2A — the protocols themselves live in `agent-stack`. |
 | **[sheleg-design](https://github.com/ssheleg/sheleg-design-skill)** | 1.66.0 | The taste layer. Cinematic scroll-driven landing pages — one scroll clock, motion that degrades to calm, WebGL particle formations — plus product-UI style packs each shipping a ready token layer, and the Figma border: tokens as variables, design to code without hand-copied values. |

package/claude-plugin-pins.json

@@ -1063,16 +1063,16 @@
     {
       "name": "task-pipeline",
       "repo": "ssheleg/task-pipeline",
-      "commit": "67715b0bf741f45a5040a581afee08d115bac580",
-      "version": "1.97.1",
+      "commit": "53b322118d48c5cca42c73515a2a399943b188ef",
+      "version": "1.98.0",
       "pluginInstall": "task-pipeline@task-pipeline",
       "pluginPath": "plugins/task-pipeline",
       "entry": {
         "name": "task-pipeline",
         "displayName": "Task Pipeline",
         "source": "./plugins/task-pipeline",
-        "description": "Runs a substantial task through a mandatory built-in intake grill, then 10 gated stages (docs, brainstorm+decompose, spec, plan, subagent build, tests, lint/deploy, post-deploy, docs/wiki, acceptance). Every stage's doctrine is built into the skill — no companion plugin required — with typed auto/judgment/manual gates, a frozen requirement spine that closes with evidence, a work board and a verification ledger that outlive a run, an exposure line naming what shipped unconfirmed, a progress rail computed from the project's own config, a loop guard whose review ceiling measures rather than stops, and stage-3 tracks for what a product does, how it sounds and how it looks. Two modes need no task: `checkup` (what is unverified) and `setup` (audit existing docs); a third, `waves`, takes the whole board and closes it in waves that each finish in one pass. Retro insights can publish upstream as issues, opt-in and redacted.",
-        "version": "1.97.1",
+        "description": "Runs a substantial task through a mandatory built-in intake grill, then 10 gated stages (docs, brainstorm+decompose, spec, plan, subagent build, tests, lint/deploy, post-deploy, docs/wiki, acceptance). Every stage's doctrine is built into the skill — no companion plugin required — with typed auto/judgment/manual gates, a frozen requirement spine that closes with evidence, a work board and a verification ledger that outlive a run, an exposure line naming what shipped unconfirmed, a progress rail computed from the project's own config, a proportional short path for small changes, a loop guard whose ceilings stop and record a blocker, and stage-3 tracks for what a product does, how it sounds and how it looks. Two modes need no task: `checkup` (what is unverified) and `setup` (audit existing docs); a third, `waves`, takes the whole board and closes it in waves that each finish in one pass. Retro insights can publish upstream as issues, opt-in and redacted.",
+        "version": "1.98.0",
         "author": {
           "name": "ssheleg",
           "url": "https://x.com/sshlg93"
@@ -1095,8 +1095,8 @@
       "files": [
         {
           "path": ".claude-plugin/plugin.json",
-          "sha256": "7fa2ae0fa4730563c288ecb6ee986d9b59602e0db91bf7dddda49cea4f3e1ddd",
-          "bytes": 1490
+          "sha256": "712a8bf0bb8b9309a7bab54e59564d4516715f06007f2a8557f24b7cf42f05c2",
+          "bytes": 1528
         },
         {
           "path": "agents/verifier-product.md",
@@ -1130,8 +1130,8 @@
         },
         {
           "path": "commands/task-pipeline.md",
-          "sha256": "90172d1b2d325e56e8d365e37023e1d21528d1ca1f06c9a1b7ecf501cb37a872",
-          "bytes": 14045
+          "sha256": "7b73fbd7138a10d528e212d0b86215aa843a8c495abf4a840c7a01ac2d699eba",
+          "bytes": 1481
         },
         {
           "path": "hooks/build-gate.sh",
@@ -1175,8 +1175,8 @@
         },
         {
           "path": "skills/evidence-docs/references/GENERATED.md",
-          "sha256": "352c733cda7175a39247dc5a43b573445c002be900ca13a85ded5f6d2cc9cf6b",
-          "bytes": 599
+          "sha256": "5db1755db9a4e67ad79062c6fe7366b9adc807b3ad6972d890faafb93146fb76",
+          "bytes": 684
         },
         {
           "path": "skills/evidence-docs/references/hooks.md",
@@ -1185,13 +1185,13 @@
         },
         {
           "path": "skills/evidence-docs/references/learned.md",
-          "sha256": "ca133eb8669e33ffc800139472c594d55b1ad91f4555251a4162c49bbb34bcd6",
-          "bytes": 33093
+          "sha256": "a5b84167ae86772741b589c1dfd19a9df6e077e406f4dcb777d99b2375d8789e",
+          "bytes": 36435
         },
         {
           "path": "skills/evidence-docs/references/retrospective.md",
-          "sha256": "9e3b0623d0ed5b4b141f271d7d3ccdbae4fc6b3fb181b7614de1b3c54c638b4f",
-          "bytes": 34725
+          "sha256": "c9f1ba9467c92d7dcd4cb3a0cf280116e5678c7946d7100215892f51f0de889f",
+          "bytes": 1300
         },
         {
           "path": "skills/evidence-docs/references/setup.md",
@@ -1200,8 +1200,8 @@
         },
         {
           "path": "skills/evidence-docs/SKILL.md",
-          "sha256": "f656ed03bc4dfec4e7a0809022838dc18e8a876905a26603ddb36b447fb83aee",
-          "bytes": 9294
+          "sha256": "b8dbb0d19b07ea3c5f6e5934fcbe56b1b1717a2438ba92edc216ec48a1c509c1",
+          "bytes": 9846
         },
         {
           "path": "skills/evidence-docs/templates/decisions.md",
@@ -1230,8 +1230,8 @@
         },
         {
           "path": "skills/project-audit/SKILL.md",
-          "sha256": "2578d22abc3fc6ffccfc55b9c63ed95edbb017b5cb61600a81553d910819fc5d",
-          "bytes": 19408
+          "sha256": "858c7deebaa0b532551ddc3747bd5f3ce7eaa8f59ed88c4f1d541658dcfd92e9",
+          "bytes": 19982
         },
         {
           "path": "skills/task-pipeline/assets/verifier-product.md",
@@ -1285,23 +1285,23 @@
         },
         {
           "path": "skills/task-pipeline/graph.schema.json",
-          "sha256": "72b6cb94f5b6eaefa6b7f6d1a1373284cfe2fe315526dd7be79bbfb82b5b4c55",
-          "bytes": 27411
+          "sha256": "29d41d1b7b22df87c7e5cf88c19253814d67b612470e2cd439c15293d0a86e09",
+          "bytes": 27505
         },
         {
           "path": "skills/task-pipeline/pipeline.example.json",
-          "sha256": "4a67e7259e6414c53a269baa579935026c955355ea1090aea575418be05b0069",
-          "bytes": 25596
+          "sha256": "253d7f3b83516933660b61e55b8756019caae182d759a2f1c5a21af9a0aba6d4",
+          "bytes": 25974
         },
         {
           "path": "skills/task-pipeline/pipeline.schema.json",
-          "sha256": "4ce237089c9c3c507e5d3fa36f093feca4f5289f6d0867debf2645c4959bd9d3",
-          "bytes": 20061
+          "sha256": "c48334fcc20bf73e9660870db299d4f4ea4c537a9f06800d681e6e0ff7245a3a",
+          "bytes": 20488
         },
         {
           "path": "skills/task-pipeline/references/acceptance.md",
-          "sha256": "dc162d9b16b166d1e7aa306d7e89d5632d4ba9ff0c0d2e559345dca114f63ae3",
-          "bytes": 25794
+          "sha256": "5d98f140690375b943885fc504f013da702231cce60dfb19b160be1405c39b23",
+          "bytes": 25790
         },
         {
           "path": "skills/task-pipeline/references/adoption.md",
@@ -1325,8 +1325,8 @@
         },
         {
           "path": "skills/task-pipeline/references/brainstorm.md",
-          "sha256": "7fd80a8eaa369800831c6c264f2f618e9dca84946240bca48aa1ed9ebbfab544",
-          "bytes": 9047
+          "sha256": "8ccdb35e99868a2558540bea4562b9fb39f50ef0cc0d1dbb4e748b9ea36006ed",
+          "bytes": 9138
         },
         {
           "path": "skills/task-pipeline/references/browser.md",
@@ -1335,13 +1335,13 @@
         },
         {
           "path": "skills/task-pipeline/references/build.md",
-          "sha256": "871f6cbf23b1a8fb4f90b995790212b70861c48b1f532a132119d71d34d2734c",
-          "bytes": 39260
+          "sha256": "eae704e0f2d6ddf7cca80ee6a7a3c1a123f2cdedd3ea48994a1df65f78250f83",
+          "bytes": 39315
         },
         {
           "path": "skills/task-pipeline/references/certification.md",
-          "sha256": "f2e17340db35ef2bd4c8da54c1c289d3e54a4f11a5f6a445ba2055a02c48e672",
-          "bytes": 17267
+          "sha256": "fe75a55722dac2eb49e1038623affec2e0cf7564eb095f3bf9147fa67d48a9e6",
+          "bytes": 17981
         },
         {
           "path": "skills/task-pipeline/references/companion-skills.md",
@@ -1370,8 +1370,8 @@
         },
         {
           "path": "skills/task-pipeline/references/doctrine-map.md",
-          "sha256": "8c2a4ebb23f00068ed351dd890e12cd44eec5df86b5f735f559c1a43cc82e9ea",
-          "bytes": 5187
+          "sha256": "7a3d933f1bc0f01701d073cbc1af8168ad78e4891f62767c8d67b99402e88f6c",
+          "bytes": 5188
         },
         {
           "path": "skills/task-pipeline/references/documentation.md",
@@ -1385,8 +1385,8 @@
         },
         {
           "path": "skills/task-pipeline/references/finish-line.md",
-          "sha256": "a63a4e6997451b5ba96aaa140bfaef638349fc657f04c6e18dbbb3b3a7a9139c",
-          "bytes": 6975
+          "sha256": "f44e710fcb5a7dc99a3cc7ea977c7942c4ce0f53b87969d6bd1f6807fffb8300",
+          "bytes": 7304
         },
         {
           "path": "skills/task-pipeline/references/gates.md",
@@ -1405,8 +1405,8 @@
         },
         {
           "path": "skills/task-pipeline/references/iteration.md",
-          "sha256": "c325d6e0981865966019830a01d292762df1b32dfed44485d2b685fb0bab5c68",
-          "bytes": 25480
+          "sha256": "c6bdb1f0c6537185a0fb3855c2a01b358b3cb91df564f19a9a28731d6d9a5af8",
+          "bytes": 25116
         },
         {
           "path": "skills/task-pipeline/references/knowledge-graph.md",
@@ -1415,18 +1415,18 @@
         },
         {
           "path": "skills/task-pipeline/references/knowledge-sources.md",
-          "sha256": "0bb0364f1993ad3e825f6f8425165c437f21cafce558983385b0eaf78df38a24",
-          "bytes": 24700
+          "sha256": "0b88ab79bb07570c03c5889bdf96d1643d39d4c39ab97cacc84e3fb4d0fdbe3f",
+          "bytes": 24949
         },
         {
           "path": "skills/task-pipeline/references/learned.md",
-          "sha256": "cbc5d5c53275875df97dabf7bbd409b7cfa400cf0f1dcb2704e83a5e5c9bb247",
-          "bytes": 31938
+          "sha256": "ff82150a71ec1f39031ed1d48c6f37ee7fb23d7a1ec20aadf4e081babde57283",
+          "bytes": 35175
         },
         {
           "path": "skills/task-pipeline/references/loop-guard.md",
-          "sha256": "1a62dde018bc1783baf6ecd1a808ce46065185007090e275aad8a50e48cbb961",
-          "bytes": 11797
+          "sha256": "f11c0e8974e6f938fcc8d9552e8801a0bd424309fa7857057e7046928572a3f2",
+          "bytes": 12455
         },
         {
           "path": "skills/task-pipeline/references/model-tiering.md",
@@ -1465,8 +1465,8 @@
         },
         {
           "path": "skills/task-pipeline/references/retrospective.md",
-          "sha256": "4b8c6b3ccc156252847c65947aa3b2fdf66e1d9ab4bc2853765f421337010fac",
-          "bytes": 33913
+          "sha256": "98f7c681065604e347531075b0f711d03d21be0d004f486b1d0d58b9a8f95247",
+          "bytes": 37119
         },
         {
           "path": "skills/task-pipeline/references/review.md",
@@ -1480,13 +1480,13 @@
         },
         {
           "path": "skills/task-pipeline/references/spec.md",
-          "sha256": "d2651b02ac11392903b1ba5510869cec499d3f96a89e0c61b7e5ab5fac24b425",
-          "bytes": 19215
+          "sha256": "f1bd6684f57b6314a3dcd85370e1e8e2fe640c9a4bedc62b00a73776442ec03d",
+          "bytes": 19382
         },
         {
           "path": "skills/task-pipeline/references/stage-00-intake.md",
-          "sha256": "4e255a02436c329d22c4b37e0aa4110d16fbc4870148c891f7331e67db553e0c",
-          "bytes": 11576
+          "sha256": "0a16e432a2b1a1f7bdb19b9e58594173df79ca3eb4d23230434a3fe08cc1efb0",
+          "bytes": 12814
         },
         {
           "path": "skills/task-pipeline/references/stage-01-docs-study.md",
@@ -1510,8 +1510,8 @@
         },
         {
           "path": "skills/task-pipeline/references/stage-05-dev.md",
-          "sha256": "53fb7e15760fd42b0a17ef20c4be8a5d5bc3e911dc469d6d255b3d700c11b648",
-          "bytes": 4227
+          "sha256": "b8e9087ec9c463e9f26929f2227d0c62425031524b8c1c9298915b140b9c9014",
+          "bytes": 4228
         },
         {
           "path": "skills/task-pipeline/references/stage-06-tests.md",
@@ -1540,8 +1540,8 @@
         },
         {
           "path": "skills/task-pipeline/references/stages.md",
-          "sha256": "d3b504e5c5718727acabd3fe7d546cb4f419ad153575915fbf980f4ba4d1a985",
-          "bytes": 35867
+          "sha256": "367dc50da058fada142ee8bf4b3036bf7f00c92d58700f547083656caea09622",
+          "bytes": 36835
         },
         {
           "path": "skills/task-pipeline/references/tdd.md",
@@ -1555,8 +1555,8 @@
         },
         {
           "path": "skills/task-pipeline/references/waves.md",
-          "sha256": "0540ba5a052c1ab69065d6012ebf8ec69a3494fbd229cf7226ba3517af06bfa1",
-          "bytes": 17641
+          "sha256": "bb436d30ca6c773602f5a3d1cd4a8f9996b3ac6c89fc2797e7a16d484df1c117",
+          "bytes": 17799
         },
         {
           "path": "skills/task-pipeline/references/work-graph.md",
@@ -1580,8 +1580,8 @@
         },
         {
           "path": "skills/task-pipeline/scripts/graph.py",
-          "sha256": "f07abf42a455676a7ca8e733bcaab371cecedb29fb16f594895b9c15a1b4b736",
-          "bytes": 111655
+          "sha256": "fa9f7c50284c2e813191a037306e80d3f89e7d50d78bc66fe118fecf7d7403c6",
+          "bytes": 114945
         },
         {
           "path": "skills/task-pipeline/scripts/lessons.py",
@@ -1598,6 +1598,16 @@
           "sha256": "0c1c2a55b9907147c9f8f5dc9075f67b050df6d79581eef4dca4c89ec33e8728",
           "bytes": 17215
         },
+        {
+          "path": "skills/task-pipeline/scripts/retro_budget.py",
+          "sha256": "0ceaec6a7d041616293923a7b4b83bfca09fe778c6e88950a0893e40a4e80e6a",
+          "bytes": 11828
+        },
+        {
+          "path": "skills/task-pipeline/scripts/short_path.py",
+          "sha256": "f68c572d4c016fa9809b7ee84c8746e6235ec475b60a6caf3fe8c555e54dcfbf",
+          "bytes": 2671
+        },
         {
           "path": "skills/task-pipeline/scripts/stage_checkpoint.py",
           "sha256": "5515ea6640751c4856f56e8416eb3020df6cf5a33831aef07e4a601d72547adc",
@@ -1610,13 +1620,13 @@
         },
         {
           "path": "skills/task-pipeline/scripts/waves.py",
-          "sha256": "937bd11092e0765cde2bda4f84a4932f056fc8b3cad8233678241e24f3a18223",
-          "bytes": 39837
+          "sha256": "1d90fca5959679bbcd99c3f25f3b3e9e95c0a7673d0fe3d6a4b1583f819e4538",
+          "bytes": 40718
         },
         {
           "path": "skills/task-pipeline/SKILL.md",
-          "sha256": "3054cbd174efd2779df62facb2b199ffda275e34eb0d7d39f3abb834596c19c3",
-          "bytes": 21033
+          "sha256": "6bcf25482327802ea5beffd78bc221d0011a4288db460eb78deb4737e902d3c0",
+          "bytes": 16195
         },
         {
           "path": "skills/task-pipeline/templates/adr.md",
@@ -1645,8 +1655,8 @@
         },
         {
           "path": "skills/task-pipeline/templates/canvas.md",
-          "sha256": "2538229860f9f21f0d47a55b865db1487d1ea594e160364d91b3b786b23bd179",
-          "bytes": 3485
+          "sha256": "4bfb2c40ccbea5b422f7371fabf4f42933d369f710f2a5536ffb47e204fb5c00",
+          "bytes": 3495
         },
         {
           "path": "skills/task-pipeline/templates/carryover.md",
@@ -1730,13 +1740,13 @@
         },
         {
           "path": "skills/task-pipeline/templates/retro-archive.md",
-          "sha256": "8028077cf0b1a77a4b2d00155faf4ae133992748e079dc847f76f2df797bd35b",
-          "bytes": 2453
+          "sha256": "5a2b7993e9f528ebf9b061b2031a5ad88e89bd4423222e3d9d2397305e50fce4",
+          "bytes": 2912
         },
         {
           "path": "skills/task-pipeline/templates/retro.md",
-          "sha256": "118a4f44fc2dbd41310b626ab96bce3c5314044ebee9de106d1bbc3a752c6e43",
-          "bytes": 4384
+          "sha256": "e513514cba82caed82b46a6c751eaeda412630d628d8a1d41da744b0e9d330e8",
+          "bytes": 5031
         },
         {
           "path": "skills/task-pipeline/templates/routing-rule.md",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sshlg-skills",
-  "version": "1.71.0",
+  "version": "1.72.0",
   "skillsCli": "skills@1.7.2",
   "description": "The ssheleg harness skill layer: routing, delivery gates, specialist skills and durable handoffs for coding agents.",
   "bin": {

package/skills.json

@@ -76,13 +76,13 @@
         "evidence-docs",
         "project-audit"
       ],
-      "version": "1.97.1",
+      "version": "1.98.0",
       "entry": "/task-pipeline",
       "role": "how a change reaches the repository",
       "npm": "task-pipeline-skill",
       "shape": "static",
       "shapeWhy": "The stage list is decided before the run and stays decided, because stage 10 has to account for what ran. THREE places discover structure, and they do not land the same way: the module map and the carry-over ledger are committed artifacts, and since v1.69.0 the work graph is a third — `.task-pipeline/graph.json`, mutated mid-run by `graph.py add` and deliberately NOT committed. Every mutation records why it happened, which is what keeps a run from explaining its completion by a plan that existed only at the end; that the graph itself does not survive the run is an open row rather than a settled decision.",
-      "commit": "67715b0bf741f45a5040a581afee08d115bac580"
+      "commit": "53b322118d48c5cca42c73515a2a399943b188ef"
     },
     {
       "name": "agent-sync",