task-pipeline-skill 1.49.1 → 1.49.2

package/CHANGELOG.md

@@ -1,5 +1,45 @@
 # Changelog
 
+## v1.49.2 — four stray table rows, and a list that promised three and delivered two
+
+### Fixed
+
+- **The body shipped a rendering defect.** Four rows of the built-in-doctrine
+  index — `artifacts.md`, `companion-skills.md`, `conventions.md`,
+  `model-tiering.md` — sat between the grill's bullet list and `## How to run`
+  with no header row above them. GFM needs a delimiter row to open a table, so an
+  agent reading `SKILL.md` saw four lines of literal pipes. Moved back into the
+  index where their shape says they belong.
+
+- **"Three things the grill does beyond clarifying the request" listed two.** The
+  displaced rows had taken the third with them. Restored from
+  `references/grill.md`, which still carries it in full: **the design
+  destination** — which Figma file, in which team, decided at stage 0 rather than
+  at drawing time. Restored rather than renumbered, because the reference proves
+  what was lost; renumbering to "two" would have made the body agree with itself
+  and disagree with the doctrine.
+
+Guards: 309 → **309**. Property checks: 9 → 9. This release restores content and
+adds no enforcement — the defect was structural markdown, which no guard here
+reads, and the count is stated because two probes read the newest section.
+
+### Note on the token budget
+
+The body is **5969 tokens against a 5000 cap**, up 108: the restored bullet costs
+more than the four moved rows save. Correctness first — a body promising three
+items and delivering two, with four lines rendering as garbage, is worse than
+being over a soft cap it was already over.
+
+The gap is now measured rather than estimated, so it stops being re-litigated by
+prose trims. Three attempts at trimming prose produced 35 tokens between them. The
+whole doctrine index is 555 tokens — 320 in the descriptive column, 235 in the
+reference names — so compressing every description to nothing closes at most **26%
+of the 1219-token gap**, and less than that if the stage numbers stay, which are
+the navigational value. The remainder lives in the Stages table's `Gate` column
+(`grep -c '^\*\*Gate' references/stages.md` → **0**: the body is its only home)
+and in the five-step operating procedure. Closing the gap therefore means moving
+content into references — a restructuring of the skill, not a trim.
+
 ## v1.49.1 — the entry states the count its own guard reads
 
 ### Fixed

package/SKILL-CARD.md

@@ -12,7 +12,7 @@ harmless.
 |---|---|
 | **Purpose** | Runs a substantial task through ten gated delivery stages — intake grill, docs study, brainstorm, spec, plan, subagent build, tests, lint/deploy, post-deploy, docs+registers, acceptance — refusing to advance until each gate passes |
 | **Owner** | ssheleg ([github.com/ssheleg/task-pipeline](https://github.com/ssheleg/task-pipeline)) |
-| **Version** | 1.49.1 |
+| **Version** | 1.49.2 |
 | **Surface** | Claude Code (filesystem skill + plugin) and the vercel `skills` CLI. **Not** uploaded to the Skills API; custom Skills do not sync across surfaces |
 | **Dependencies** | None required. Optional: `context7` (MCP), `figma` (MCP), super-ux, agent-sync, graphify, obsidian-wiki. Every stage's doctrine ships in-repo; the one conditional requirement is super-ux for the stage-3 UX track on a user-facing task |
 | **Evaluation status** | Suite authored, 5 categories. One recorded run, **self-observed by the author**; **zero blind runs on zero of three models** — the split, and the numbers, live in [`evals/RESULTS.md`](evals/RESULTS.md) and are computed by `evals/run.py` |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "task-pipeline-skill",
-  "version": "1.49.1",
+  "version": "1.49.2",
   "description": "Full-cycle delivery pipeline for coding agents: a mandatory built-in intake grill, then 10 gated stages (docs, brainstorm+decompose, spec, plan, build, tests, lint/deploy, post-deploy, docs/wiki, acceptance). Every stage's doctrine ships inside the skill — no companion plugin required. This package is the installer CLI.",
   "bin": {
     "task-pipeline": "bin/task-pipeline.js"

package/plugins/task-pipeline/.claude-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "task-pipeline",
   "displayName": "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/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). Retro insights can publish upstream as issues, opt-in and redacted.",
-  "version": "1.49.1",
+  "version": "1.49.2",
   "author": {
     "name": "ssheleg",
     "url": "https://x.com/sshlg93"

package/plugins/task-pipeline/skills/task-pipeline/SKILL.md

@@ -73,6 +73,10 @@ gate stops until it is installed.
 | run-wide · the work-list **between** runs, and how its priority is computed | `references/backlog.md` |
 | run-wide · whether a **human** ever confirmed what shipped, and when | `references/verification.md` |
 | run-wide · how much unconfirmed work has piled up, and what to look at first | `references/exposure.md` |
+| any stage · Where each artifact belongs | `references/artifacts.md` |
+| preflight · Companion skills and their fallbacks | `references/companion-skills.md` |
+| 6–10 · How the host project's CLAUDE.md is read | `references/conventions.md` |
+| preflight · Model map, ids and the override | `references/model-tiering.md` |
 
 **Optional bridge.** An equivalent skill set the operator already runs (e.g.
 `superpowers:brainstorming` / `writing-plans` / `subagent-driven-development` /
@@ -152,10 +156,12 @@ Three things the grill does beyond clarifying the request:
   mid-flight (test/lint/deploy commands, branch policy, log locations, docs
   targets, the model decision, deploy authorization). Autonomy is bought here or
   not at all — an unasked question is a scheduled interruption.
-| any stage · Where each artifact belongs | `references/artifacts.md` |
-| preflight · Companion skills and their fallbacks | `references/companion-skills.md` |
-| 6–10 · How the host project's CLAUDE.md is read | `references/conventions.md` |
-| preflight · Model map, ids and the override | `references/model-tiering.md` |
+- **The design destination**, when the project designs in Figma: *which* file, in
+  which team — a stage-0 decision, never a stage-3 side effect. Left to drawing
+  time the question is answered by whoever is holding the brush, and the answer is
+  usually *create a new file* — which is how a project ends up with three files
+  called some variation of "Design", each with real work in it and no way to tell
+  which one the team opens.
 
 ## How to run