@sylad/cadence 1.6.0 → 1.7.0

package/docs/lead-workflow-light.svg

@@ -0,0 +1,200 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1650 810" width="1650" height="810" role="img" font-family="-apple-system,BlinkMacSystemFont,'Segoe UI',Helvetica,Arial,sans-serif" font-size="13" fill="#1f2328">
+<title>Workflow of the lead skill in three lanes: the human, the lead session, and the orchestrate program with its agents</title>
+<defs><marker id="arr" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="7" markerHeight="7" orient="auto-start-reverse"><path d="M0,0 L10,5 L0,10 z" fill="#57606a"/></marker>
+<marker id="arrw" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="7" markerHeight="7" orient="auto-start-reverse"><path d="M0,0 L10,5 L0,10 z" fill="#cf222e"/></marker></defs>
+<rect width="1650" height="810" fill="#ffffff"/>
+<text x="825" y="34" text-anchor="middle" font-size="18" font-weight="600">The lead workflow: decide at the top, work in fresh sessions</text>
+<rect x="10" y="70" width="1630" height="200" fill="#f6f8fa" stroke="#d0d7de"/>
+<line x1="150" y1="70" x2="150" y2="270" stroke="#d0d7de"/>
+<text x="24" y="146" font-weight="700" font-size="15" fill="#bf8700">Human</text>
+<text x="24" y="166" font-size="11.5" fill="#57606a">chooses, answers,</text>
+<text x="24" y="181" font-size="11.5" fill="#57606a">gives the UX verdict</text>
+<rect x="10" y="270" width="1630" height="200" fill="#ffffff" stroke="#d0d7de"/>
+<line x1="150" y1="270" x2="150" y2="470" stroke="#d0d7de"/>
+<text x="24" y="339" font-weight="700" font-size="15" fill="#0969da">Lead session</text>
+<text x="24" y="359" font-size="11.5" fill="#57606a">stays small:</text>
+<text x="24" y="374" font-size="11.5" fill="#57606a">reads, decides, checks,</text>
+<text x="24" y="389" font-size="11.5" fill="#57606a">delivers</text>
+<rect x="10" y="470" width="1630" height="320" fill="#f6f8fa" stroke="#d0d7de"/>
+<line x1="150" y1="470" x2="150" y2="790" stroke="#d0d7de"/>
+<text x="24" y="606" font-weight="700" font-size="15" fill="#1a7f37">orchestrate</text>
+<text x="24" y="626" font-size="11.5" fill="#57606a">program and agents</text>
+<text x="24" y="641" font-size="11.5" fill="#57606a">(fresh short sessions)</text>
+<text x="240" y="88" text-anchor="middle" font-size="11.5" font-weight="600" fill="#57606a">1 Tour</text>
+<text x="420" y="88" text-anchor="middle" font-size="11.5" font-weight="600" fill="#57606a">2 Wave</text>
+<text x="600" y="88" text-anchor="middle" font-size="11.5" font-weight="600" fill="#57606a">3 Relay</text>
+<text x="780" y="88" text-anchor="middle" font-size="11.5" font-weight="600" fill="#57606a">4 Review</text>
+<text x="960" y="88" text-anchor="middle" font-size="11.5" font-weight="600" fill="#57606a">5 Re-check</text>
+<text x="1140" y="88" text-anchor="middle" font-size="11.5" font-weight="600" fill="#57606a">6 Delivery</text>
+<text x="1320" y="88" text-anchor="middle" font-size="11.5" font-weight="600" fill="#57606a">7 Threshold</text>
+<text x="1500" y="88" text-anchor="middle" font-size="11.5" font-weight="600" fill="#57606a">8 Close</text>
+<g id="tour"><rect x="161" y="337" width="158" height="66" rx="8" fill="#ddf4ff" stroke="#0969da" stroke-width="1.5"/>
+<text x="240" y="358.5" text-anchor="middle" font-weight="600" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">cadence lead tour</text>
+<text x="240" y="374.5" text-anchor="middle">one line per project</text>
+<text x="240" y="390.5" text-anchor="middle">+ three proposals</text>
+</g>
+<g id="choose"><rect x="161" y="137" width="158" height="66" rx="8" fill="#fff8c5" stroke="#bf8700" stroke-width="1.5"/>
+<text x="240" y="158.5" text-anchor="middle" font-weight="600">Picks the lots</text>
+<text x="240" y="174.5" text-anchor="middle">and the order</text>
+<text x="240" y="190.5" text-anchor="middle">(the priority)</text>
+</g>
+<g id="launch"><rect x="341" y="337" width="158" height="66" rx="8" fill="#ddf4ff" stroke="#0969da" stroke-width="1.5"/>
+<text x="420" y="358.5" text-anchor="middle" font-weight="600">Starts the wave</text>
+<text x="420" y="374.5" text-anchor="middle" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">orchestrate … --wave</text>
+<text x="420" y="390.5" text-anchor="middle">in the background</text>
+</g>
+<g id="precheck"><rect x="161" y="508" width="158" height="82" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5" stroke-dasharray="5 3"/>
+<text x="240" y="529.5" text-anchor="middle" font-weight="600">Precheck</text>
+<text x="240" y="545.5" text-anchor="middle">local model or Sonnet:</text>
+<text x="240" y="561.5" text-anchor="middle">already delivered?</text>
+<text x="240" y="577.5" text-anchor="middle">yes → back to lead</text>
+</g>
+<g id="spec"><rect x="341" y="480" width="158" height="66" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5" stroke-dasharray="5 3"/>
+<text x="420" y="501.5" text-anchor="middle" font-weight="600">Spec (screen: page)</text>
+<text x="420" y="517.5" text-anchor="middle">spec-writer: mockup</text>
+<text x="420" y="533.5" text-anchor="middle">+ sheet, 1440 / 390</text>
+</g>
+<g id="mockup"><rect x="521" y="480" width="158" height="66" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5" stroke-dasharray="5 3"/>
+<text x="600" y="501.5" text-anchor="middle" font-weight="600">Mockup review</text>
+<text x="600" y="517.5" text-anchor="middle">ux-reviewer, 2 passes</text>
+<text x="600" y="533.5" text-anchor="middle">max, then handed back</text>
+</g>
+<g id="backspec"><rect x="341" y="552" width="158" height="66" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5" stroke-dasharray="5 3"/>
+<text x="420" y="573.5" text-anchor="middle" font-weight="600">Back-end spec</text>
+<text x="420" y="589.5" text-anchor="middle">spec: true: cases,</text>
+<text x="420" y="605.5" text-anchor="middle">rules, contracts</text>
+</g>
+<g id="sheetreview"><rect x="521" y="552" width="158" height="66" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5" stroke-dasharray="5 3"/>
+<text x="600" y="573.5" text-anchor="middle" font-weight="600">Sheet review</text>
+<text x="600" y="589.5" text-anchor="middle">code-reviewer, 2</text>
+<text x="600" y="605.5" text-anchor="middle">passes max</text>
+</g>
+<g id="accept"><rect x="701" y="480" width="158" height="138" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5" stroke-dasharray="5 3"/>
+<text x="780" y="543" text-anchor="middle" font-weight="600">Accept</text>
+<text x="780" y="559" text-anchor="middle">red tests + lock</text>
+<text x="780" y="575" text-anchor="middle">if accept declared</text>
+</g>
+<g id="implement"><rect x="341" y="650" width="158" height="66" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5"/>
+<text x="420" y="671.5" text-anchor="middle" font-weight="600">Implementation</text>
+<text x="420" y="687.5" text-anchor="middle">test first, commits</text>
+<text x="420" y="703.5" text-anchor="middle">cite the lot</text>
+</g>
+<g id="relay"><rect x="521" y="337" width="158" height="66" rx="8" fill="#ddf4ff" stroke="#0969da" stroke-width="1.5"/>
+<text x="600" y="358.5" text-anchor="middle" font-weight="600">Relays the journal</text>
+<text x="600" y="374.5" text-anchor="middle" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">tail -F journal.log</text>
+<text x="600" y="390.5" text-anchor="middle">one sentence per line</text>
+</g>
+<g id="answer"><rect x="521" y="137" width="158" height="66" rx="8" fill="#fff8c5" stroke="#bf8700" stroke-width="1.5"/>
+<text x="600" y="158.5" text-anchor="middle" font-weight="600">Answers a question</text>
+<text x="600" y="174.5" text-anchor="middle">the lead never</text>
+<text x="600" y="190.5" text-anchor="middle">answers for them</text>
+</g>
+<g id="uxpass"><rect x="521" y="650" width="158" height="66" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5" stroke-dasharray="5 3"/>
+<text x="600" y="671.5" text-anchor="middle" font-weight="600">UX pass</text>
+<text x="600" y="687.5" text-anchor="middle">visible lot + app</text>
+<text x="600" y="703.5" text-anchor="middle">declared; vs mockup</text>
+</g>
+<g id="codereview"><rect x="701" y="650" width="158" height="66" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5"/>
+<text x="780" y="671.5" text-anchor="middle" font-weight="600">Code review</text>
+<text x="780" y="687.5" text-anchor="middle">Opus (Sonnet ≤ 0.25 d)</text>
+<text x="780" y="703.5" text-anchor="middle">records raf review</text>
+</g>
+<g id="fix"><rect x="881" y="650" width="158" height="66" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5" stroke-dasharray="5 3"/>
+<text x="960" y="671.5" text-anchor="middle" font-weight="600">Correction</text>
+<text x="960" y="687.5" text-anchor="middle">new session, 2 passes</text>
+<text x="960" y="703.5" text-anchor="middle">3rd if it converges</text>
+</g>
+<g id="table"><rect x="701" y="337" width="158" height="66" rx="8" fill="#ddf4ff" stroke="#0969da" stroke-width="1.5"/>
+<text x="780" y="358.5" text-anchor="middle" font-weight="600">Final table</text>
+<text x="780" y="374.5" text-anchor="middle">ready · handed back</text>
+<text x="780" y="390.5" text-anchor="middle">· « livrable jusqu'à »</text>
+</g>
+<g id="recheck"><rect x="881" y="337" width="158" height="66" rx="8" fill="#ddf4ff" stroke="#0969da" stroke-width="1.5"/>
+<text x="960" y="358.5" text-anchor="middle" font-weight="600">Re-verifies itself</text>
+<text x="960" y="374.5" text-anchor="middle">git log · tests · build</text>
+<text x="960" y="390.5" text-anchor="middle" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">raf check</text>
+</g>
+<g id="uxverdict"><rect x="881" y="137" width="158" height="66" rx="8" fill="#fff8c5" stroke="#bf8700" stroke-width="1.5"/>
+<text x="960" y="158.5" text-anchor="middle" font-weight="600">Looks at the captures</text>
+<text x="960" y="174.5" text-anchor="middle">UX verdict →</text>
+<text x="960" y="190.5" text-anchor="middle" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">raf ux (visible lot)</text>
+</g>
+<g id="done"><rect x="1061" y="337" width="158" height="66" rx="8" fill="#ddf4ff" stroke="#0969da" stroke-width="1.5"/>
+<text x="1140" y="358.5" text-anchor="middle" font-weight="600" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">raf done</text>
+<text x="1140" y="374.5" text-anchor="middle">then push</text>
+<text x="1140" y="390.5" text-anchor="middle" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">cadence deliver</text>
+</g>
+<g id="qa"><rect x="1061" y="650" width="158" height="66" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5" stroke-dasharray="5 3"/>
+<text x="1140" y="671.5" text-anchor="middle" font-weight="600">qa-reviewer</text>
+<text x="1140" y="687.5" text-anchor="middle">reads only; blocking</text>
+<text x="1140" y="703.5" text-anchor="middle">findings → the human</text>
+</g>
+<g id="ctx"><rect x="1241" y="337" width="158" height="66" rx="8" fill="#ddf4ff" stroke="#0969da" stroke-width="1.5"/>
+<text x="1320" y="358.5" text-anchor="middle" font-weight="600">Context under 60 %?</text>
+<text x="1320" y="374.5" text-anchor="middle" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">session context</text>
+<text x="1320" y="390.5" text-anchor="middle">error = at threshold</text>
+</g>
+<g id="next"><rect x="1241" y="650" width="158" height="66" rx="8" fill="#dafbe1" stroke="#1a7f37" stroke-width="1.5"/>
+<text x="1320" y="671.5" text-anchor="middle" font-weight="600">Next wave</text>
+<text x="1320" y="687.5" text-anchor="middle" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">… --continue</text>
+<text x="1320" y="703.5" text-anchor="middle">draws the next ready lot</text>
+</g>
+<g id="close"><rect x="1421" y="337" width="158" height="66" rx="8" fill="#ddf4ff" stroke="#0969da" stroke-width="1.5"/>
+<text x="1500" y="358.5" text-anchor="middle" font-weight="600">Close</text>
+<text x="1500" y="374.5" text-anchor="middle" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">session-close</text>
+<text x="1500" y="390.5" text-anchor="middle" font-family="ui-monospace,SFMono-Regular,Menlo,monospace" font-size="11.5">session next ×3</text>
+</g>
+<g id="report"><rect x="1421" y="137" width="158" height="66" rx="8" fill="#fff8c5" stroke="#bf8700" stroke-width="1.5"/>
+<text x="1500" y="158.5" text-anchor="middle" font-weight="600">One line per project</text>
+<text x="1500" y="174.5" text-anchor="middle">delivered · in progress</text>
+<text x="1500" y="190.5" text-anchor="middle">· blocked (and why)</text>
+</g>
+<polyline points="240,337 240,203" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="248" y="236" text-anchor="start" font-size="11" fill="#57606a" class="lbl">proposals</text>
+<polyline points="319,170 420,170 420,337" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="414" y="164" text-anchor="end" font-size="11" fill="#57606a" class="lbl">choice</text>
+<polyline points="499,683 521,683" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="679,683 701,683" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="859,683 881,683" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="960,650 960,632 820,632 820,650" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="968" y="626" text-anchor="start" font-size="11" fill="#57606a" class="lbl">then review again</text>
+<polyline points="870,683 870,430 780,430 780,403" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="876" y="446" text-anchor="start" font-size="11" fill="#57606a" class="lbl">wave ends</text>
+<polyline points="510,683 510,430 600,430 600,403" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="516" y="646" text-anchor="start" font-size="11" fill="#57606a" class="lbl">journal</text>
+<polyline points="630,337 630,203" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="636" y="236" text-anchor="start" font-size="11" fill="#57606a" class="lbl">question</text>
+<polyline points="570,203 570,337" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="564" y="236" text-anchor="end" font-size="11" class="lbl" fill="#57606a">--resume --answer</text>
+<polyline points="859,370 881,370" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="960,203 960,337" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="968" y="236" text-anchor="start" font-size="11" fill="#57606a" class="lbl">on the human's verdict,</text>
+<text x="968" y="251" text-anchor="start" font-size="11" fill="#57606a" class="lbl">or the lead's (lead.ux: lead)</text>
+<polyline points="1039,370 1061,370" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="1140,403 1140,650" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="1320,403 1320,650" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="1326" y="440" text-anchor="start" font-size="11" fill="#57606a" class="lbl">yes: chain</text>
+<polyline points="1399,370 1421,370" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="1410" y="329" text-anchor="middle" font-size="11" fill="#57606a" class="lbl">≥ 60 %: close</text>
+<polyline points="1500,337 1500,203" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="1320,716 1320,746 420,746 420,716" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="870" y="740" text-anchor="middle" font-size="11" fill="#57606a" class="lbl">next wave: back to step 2, the limits still apply</text>
+<rect x="170" y="760" width="22" height="14" rx="3" fill="none" stroke="#57606a" stroke-dasharray="5 3"/>
+<text x="200" y="771" font-size="11.5" fill="#57606a">conditional step</text>
+<text x="340" y="771" font-size="11.5" fill="#57606a">The lead never commits where a wave runs, and never delivers two projects at once. At most as many sessions or subagents as the cap the human sets (CADENCE_MAX_SESSIONS, 2 by default).</text>
+<polyline points="420,403 420,440 240,440 240,508" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="319,549 330,549 330,513 341,513" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="330,549 330,585 341,585" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="499,513 521,513" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="679,513 701,513" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="499,585 521,585" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="679,585 701,585" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="240,590 240,683 341,683" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<polyline points="780,618 780,634 420,634 420,650" fill="none" stroke="#57606a" stroke-width="1.6" marker-end="url(#arr)"/>
+<text x="232" y="640" text-anchor="end" font-size="11" fill="#57606a" class="lbl">other lots</text>
+<text x="232" y="655" text-anchor="end" font-size="11" fill="#57606a" class="lbl">go straight on</text>
+<text x="890" y="508" text-anchor="start" font-size="11" fill="#57606a" class="lbl">lots with screen: page</text>
+<text x="890" y="523" text-anchor="start" font-size="11" fill="#57606a" class="lbl">spec, mockup, accept</text>
+<text x="890" y="568" text-anchor="start" font-size="11" fill="#57606a" class="lbl">lots with spec: true</text>
+<text x="890" y="583" text-anchor="start" font-size="11" fill="#57606a" class="lbl">spec, sheet review, accept</text>
+</svg>

package/docs/lead.md

@@ -0,0 +1,147 @@
+# The lead workflow
+
+The `lead` skill pilots several projects from a parent folder. Its session stays small: it reads
+summaries, decides with the human, and leaves the work to fresh short sessions run by a program
+(`cadence orchestrate`). This page draws who does what, in three lanes: the **human**, the
+**lead session**, and the **`orchestrate` program with its agents**.
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="lead-workflow-dark.svg">
+  <img alt="The lead workflow in three lanes (human, lead session, orchestrate program and agents), from the tour of the projects to the close of the session" src="lead-workflow-light.svg">
+</picture>
+
+Dashed boxes are conditional steps: the precheck runs only for a lot without a commit yet (unless `orchestrate.precheck: false`), and the spec, sheet review and accept steps run only for a `screen: page` lot or a `spec: true` lot. The skill itself is `skills/lead/SKILL.md`; this page is its
+picture, not its source.
+
+## The steps
+
+1. **Tour.** The lead runs `cadence lead tour` (a program, no model) and reports one row per project.
+   It proposes three items: finish what is in progress, then drift that blocks a delivery, then ready
+   quick wins. It stops and waits: the human picks the lots and the order (`--priority`, or the
+   `priority:` list of the parent folder's `cadence.yaml`).
+2. **Wave.** The lead starts `cadence orchestrate <project>:<lot> … --wave <id>` in the background.
+   For each lot the program runs, in fresh sessions and in this order: `precheck → spec → maquette →
+   accept → implement → review → ux`. The **precheck** applies to any lot without a commit yet (unless
+   `orchestrate.precheck: false`). The spec steps exist only for a lot that declares
+   a `screen:` of `page` (a visible lot that creates or changes a whole screen; `screen: component` and `screen: journey`
+   lots take the ordinary path, straight to the implementation, unless they already have a sheet) or `spec: true` (a lot without a screen
+   that still has a behaviour to pin down: `precheck → spec → fiche → accept → implement → review`);
+   spec, sheet review and accept apply to `screen: page` and to `spec: true` alike; the other lots go
+   straight from the precheck (when it applies) to the implementation:
+   - **spec**: the `spec-writer` agent draws a static mockup to the project's own style and writes the
+     screen sheet (`fiche.yaml`: fields, states, numbered rules), rendered at 1440 and 390 px;
+   - **fiche** (a lot with a back-end part: `spec: true`, or a screen lot whose sheet has a `sujet` block):
+     the `code-reviewer` agent in sheet mode reviews the back-end sheet (two passes at most, then the lot
+     is handed back) unless `orchestrate.fiche: false`; a mixed lot has both reviews, and their findings
+     go together to a single second `spec` pass. A lot without a screen has no News entry: the
+     hypotheses of its final sheet become one note of the lot each, and the end-of-wave table lists them
+     as `hypothèse de la fiche : …` — the lead relays them to the human;
+   - **maquette**: the `ux-reviewer` agent reviews the mockup (two passes at most, then the lot is handed
+     back) unless `orchestrate.maquette: false`;
+   - **accept**: a separate session writes the acceptance tests from the sheet, committed red and locked,
+     when the project declares `orchestrate.accept`; without it the step is skipped with a warning;
+   - the implementation (test first, commits citing the lot) makes them green without touching them;
+   - a UX pass if the lot is `visible` and the project says how to see its app (`orchestrate.ux`); for a
+     lot with a sheet it is a conformity pass against the mockup;
+   - the code review (Opus; Sonnet for a lot of 0.25 day or less), which also follows each rule of the
+     sheet to its test;
+   - a correction in a new session if the review is not compliant (two passes at most, a third when the review
+     converges — blocking + major findings down and only one left —, each followed by a review).
+
+   The program records `raf review` itself once the review is compliant.
+3. **Relay.** The lead follows the wave's journal (`tail -n +1 -F .cadence/runs/<id>/journal.log`, one
+   line per transition) and tells the human each line in one sentence, with no polling loop. A
+   question from a session comes back to the human at once; the answer goes in with
+   `cadence orchestrate --resume --answer <project>:<lot> "…"`. The lead never answers in the
+   human's place. `--drop` and `--stop-after-current` steer a wave that is running.
+4. **Review.** The final table of the wave lists the lots ready, handed back, and the line
+   « livrable jusqu'à <sha> » for a ready lot stacked under a handed-back one. Minor findings come back in
+   the table: one becomes a lot of its own only if it describes an observable bug.
+5. **Re-check.** The lead verifies itself, one project at a time: `git log`, the test suite and the
+   build run by the lead, `raf check` clean. A `visible` lot waits for the human to look at the
+   UX reviewer's captures: the lead records `raf ux` on the human's verdict, never on its own — unless the parent folder's `cadence.yaml` says `lead.ux: lead`: then the lead forms the verdict from the reviewer's report and its own look at the captures, and asks the human only at the slightest doubt. Then
+   `raf done`.
+6. **Delivery.** Push (for a « livrable jusqu'à <sha> », that sha alone, never HEAD), then
+   `cadence deliver`. After a green delivery that changes what a page shows or what it is served, the
+   `qa-reviewer` agent walks the delivered pages in a real browser, reads only, and brings its blocking
+   findings to the human. It is not a gate: a finding becomes a new lot.
+7. **Threshold and chaining.** Before every new wave the lead reads `cadence session context`. Under
+   **60 %** it chains: `cadence orchestrate --continue` draws the next ready lot of the plan, in the
+   declared priority, without asking the human « next? ». From 60 % upward, or when the figure cannot
+   be read (exit code 2: the band is not loaded, or its figure is stale), it starts nothing. A lot
+   that was not handed back ready is reported, not chained over; a question or a UX reservation
+   pending on a lot never stops the chain on the other lots.
+8. **Close.** `session-close` in each project touched, filtered memory, three lines for next time
+   with `cadence session next` (the wave that was about to start comes first), then one line per project
+   to the human: delivered, in progress, blocked (and why).
+
+## Permanent rules
+
+| Rule | Why |
+|---|---|
+| At most **as many subagents as the session cap** running at once (2 by default; the human sets it with `CADENCE_MAX_SESSIONS`), orchestrate sessions included | `cadence orchestrate --status` and `cadence lead tour` print `créneaux libres : N sur M`, M being the configured cap; the lead never raises `--max-sessions` or `CADENCE_MAX_SESSIONS` itself |
+| Never two sessions in the same repository at the same time; the lead does not commit where a wave runs | a wave's lock refuses `cadence deliver` while a lot still works there |
+| A locked acceptance test that contradicts the sheet is corrected by the lead with `cadence spec reseal <lot> <test> --reason "…"` (lot in progress, outside a wave; an amended sheet is accepted once committed, every commit that touched it citing the lot, L217, never put it back to the red state; a delivered lot with an unstable test: add `--porteur <lot in progress>`, L212), then `--resume --answer` for a lot in question, or a new `cadence orchestrate <project>:<lot>` for a lot handed back (`--resume` skips it) | never by a session, never by editing `acceptation.json` |
+| Deliveries and the `raf ux` / `raf review` verdicts belong to the lead, one project at a time | never to a subagent, never two deliveries in parallel |
+| The UX verdict is the human's unless `lead.ux: lead` (parent `cadence.yaml`, default `human`) | then the lead decides from the report and the captures, and brings any doubt to the human |
+| A session cannot ask the human anything | it stops and reports; the lead brings the question back |
+| Never push or deliver HEAD above a handed-back lot | HEAD holds code that was not reviewed |
+| A plan kept by another tool is read-only for `raf` | its own commands record the lot's state |
+
+## Exit codes
+
+`cadence orchestrate`:
+
+| Code | Meaning |
+|---|---|
+| `0` | every lot is ready |
+| `1` | some lots were handed back to the lead |
+| `2` | refused before acting (a precondition failed) |
+| `3` | wave suspended (budget or usage limit); `--resume --budget …` continues |
+
+`cadence session context` exits `2` when it cannot prove the figure (no band, several sessions in
+the folder without `$CLAUDE_CODE_SESSION_ID`, figure older than two minutes): the lead then treats it
+as being at the threshold.
+
+The mechanics around it (the life of a lot in the plan, a lot inside a wave, putting cadence in service, the budgets) are drawn in
+[fonctionnement.md](fonctionnement.md). See also the [lead tour](lead.md#lead-tour) section below and the [orchestrate](orchestrate.md#orchestrate)
+page.
+
+## lead tour
+
+`cadence lead tour [folder] [--idle 3] [--depth n] [--json]` is the lead's morning table, with no model in
+the loop. From a parent folder (default: the current one) it takes every direct sub-folder that
+holds `docs/plan/raf.yaml`, or a `cadence.yaml` with a `plan:` key (a plan kept by another tool
+included), and for each one reads the same facts as `cadence session start` — in-process, no
+sub-process, no call to `claude` — then prints **one line per project**:
+
+```
+alpha · en cours L1 (silencieux 4j) · dérive 1 (✗ L2 a 1 commit(s) mais est encore todo) · notes : finir L1 puis livrer · prochain L3 Typo · dépôt non commité, non poussé
+beta · en cours rien · dérive aucune · notes : aucune · prochain T2 Second · dépôt propre
+```
+
+| Column | Content |
+|---|---|
+| `en cours` | ids of the lots in progress; `(aucune activité)` when it has none at all, `(silencieux Nj)` when the lot's last activity (commit, note or start) is more than `--idle` days old (default 3) |
+| `dérive` | the gaps `raf check` reports (a lot whose commits leave a document behind, [`docs.sync`](news.md#documentation-that-follows-the-code), included), counted and the first two shown |
+| `notes` | the notes left by the last `session close`, joined with ` / ` and cut at 120 characters |
+| `prochain` | the first ready lot (quick wins first) — id and title cut at 60 characters; a lot whose [`gate`](raf.md#plan-file) is not met is not ready |
+| `attend` | only when a lot waits on its `gate`: `attend L190` |
+| `dépôt` | `non commité` (modified or untracked files), `non poussé` (commits ahead of the upstream), `livraison en cours` (live delivery lock); `propre` otherwise |
+
+When an orchestrated wave is live, one more line closes the tour (not part of `--json`): `vagues en cours : 1 · sessions en cours : 0 · créneaux libres : 1 sur 2` — the lead reads the free slots there instead of computing them (L141). The `sur M` is the cap the human set (`CADENCE_MAX_SESSIONS`, 2 by default), not a fixed 2 (L208); an invalid value falls back to 2 in this display.
+
+`--json` prints the same content as an array of objects (`project`, `doing`, `drift`, `notes`, `waiting` (only when a lot waits on its `gate`),
+`next`, `repo`, and `error` when the project could not be read), plus `progress` — `{ done, doing, todo, added7 }`,
+the lots done / in progress / to do (dropped and recurring lots left out) and those created in the last 7 days (L149), which
+[`cadence-hud`](../plugins/cadence-hud/README.md) draws as one progress bar per project. Projects come in the order of the
+`priority:` key of the folder's `cadence.yaml` (the one `orchestrate --continue` reads), the others after, alphabetically; an unreadable `cadence.yaml` or
+a `priority:` that is not a list of names (`priority: ol`, `priority: []`) keeps the alphabetical order and adds a first row `cadence.yaml · ✗ erreur : <cause>` (`project: "cadence.yaml"` with `error` in `--json`).
+Sub-projects are looked for one level down by default. `--depth n` goes `n` levels down (same meaning as in `cadence session start --all --depth n`:
+a folder that is a project is not entered; an integer ≥ 1, otherwise refused), and the `depth:` key of the folder's `cadence.yaml`, next to `priority:`, sets it once for all
+(`depth: 2`); `--depth` wins over the key, and a `depth:` that is not an integer ≥ 1 adds the same first row `cadence.yaml · ✗ erreur : …` and leaves one level read.
+`cadence-hud` asks the tour from the folder of the session, so it follows the key with no change. A project is named by its folder's name; one found below the first level is named by its path from the folder (`groupe/gamma`), unique and ready for `cadence orchestrate groupe/gamma:L1` run from there, while `priority:` and the alphabetical order read the folder's own name.
+"Created in the last 7 days" means today and the six days before. When the folder has no sub-project but is itself a project, the tour is that project's single line
+(this is what `cadence-hud` asks from a session opened inside a project). The tour is read-only: it changes
+no plan. It exits 0 even when a project is in error — that project's line reads
+`beta · ✗ erreur : <cause>`. The `lead` skill runs it instead of one subagent per project.

package/docs/news.md

@@ -0,0 +1,245 @@
+[← cadence](../README.md)
+
+# news
+
+What changed *for the user*, one entry per visible lot, each with a screenshot.
+
+- Mark a lot as user-facing with `raf add … --visible` (or `visible: true` in
+  the YAML). `raf done` and the post-commit hook remind you to write its entry;
+  `raf check` fails while a visible lot is done without one.
+- An entry is a Markdown file in `docs/nouveautes/`, with a YAML header.
+  Screenshots are files you take yourself, stored next to the entries.
+- `cadence news build` writes `nouveautes.json` for your app to display, a
+  self-contained `index.html`, and copies the screenshots.
+
+```sh
+raf add "Amounts like 3.000 read as three thousand" --visible   # → L8
+raf start L8 && git commit -m "fix(L8): thousands separator" && raf done L8
+cadence news new L8          # docs/nouveautes/2026-09-29-amounts-like-3-000-….md (title: the lot's public title if any)
+# add docs/nouveautes/captures/l8.png, list it under `captures:`, write the text
+cadence news check           # exit 1 on drift (also part of raf check)
+cadence news build -o frontend/public/nouveautes
+```
+
+```markdown
+---
+title: Amounts like 3.000 read as three thousand
+date: 2026-09-29
+created: 2026-09-29T14:32+02:00
+lots: [L8]
+captures: [captures/l8.png]
+# nocapture: reason, when a screenshot makes no sense
+---
+Imported statements now read **3.000** as three thousand, not three.
+```
+
+A screenshot can say what it shows: write it as `{ file, alt }` instead of a
+bare path, one text per screenshot.
+
+```yaml
+captures:
+  - { file: captures/l8-before.png, alt: "Statement total read as 3 instead of 3,000" }
+  - captures/l8-after.png          # a bare path still works: no alternative text
+```
+
+| Command | Effect |
+|---|---|
+| `cadence news new <lot…> [--title t]` | entry skeleton, dated and timed now (`date`, `created`), titled after the lot's public title (`public`), else its title; `--title` wins |
+| `cadence news list` | entries, newest first (see *Order* below) |
+| `cadence news check` | visible lots done without entry, unknown lots, missing or undeclared screenshots, entries without creation time, bad headers, a lot whose screen sheet has hypotheses and whose entry lacks the `## Hypothèses` section (or a line for one of them) |
+| `cadence news stamp` | migration: writes `created:` into entries without one (or with an empty one), from the author date of the commit that added the file under its current name (now if not committed yet) |
+| `cadence news build [-o dir]` | `nouveautes.json` + `index.html` + screenshots (default `docs/nouveautes/site`) |
+
+`--dir` changes the entries folder (default `docs/nouveautes` at the git root).
+The Markdown is deliberately small: headings (`#` to `######`, rendered one level lower, `<h2>` to `<h6>`; a heading takes its own line and cuts the paragraph or list around it), paragraphs, `-` lists (a bullet may continue on the next lines, indented), `**bold**`,
+`` `code` ``, `[links](../url)`; everything else is escaped text. The JSON holds
+`{ project, generated, entries: [{ slug, title, date, lots, captures, html }] }`,
+with screenshot paths relative to the JSON file. `captures` is always a list of
+paths; an entry that gives at least one alternative text also carries `alts`,
+the texts in the same order (`""` for a screenshot without one) — an entry
+without any keeps exactly the shape above. The built page puts the text in the
+image's `alt`, and falls back to "Capture : <title>".
+
+**Order.** Everywhere (`list`, `build`, the JSON), entries are strictly newest
+first: by `date`, then, on the same day, by creation time. Every entry carries
+it to the minute in its `created` header, which `cadence news new` writes as
+local time with an explicit offset (`2026-09-29T14:32+02:00`, or `Z`). The
+offset is required, so the order does not depend on the machine's time zone:
+`news check` (and `raf check`) flags a value without it, an impossible one, an
+empty `created:`, and an entry without `created`. `cadence news stamp` fills
+it in older entries (or replaces an empty one) from the author date of the
+commit that added the file under its current name; until then, that date is
+used for sorting (an entry not committed yet counts as the newest). Renames
+are not followed: a renamed entry counts as added on the day of the rename,
+so stamp it before renaming it. The file name only breaks the remaining ties,
+since it follows the title, not the chronology. The page and the JSON still
+show the day only.
+
+## UX review
+
+```sh
+raf ux enable                      # from today, a --visible lot needs a UX review before done
+raf ux L4 "compliant after 2 fixes"   # record the verdict (from the ux-reviewer agent)
+raf ux L8 "no screen: calculation fix"
+```
+
+With the rule on, `raf done` refuses a visible lot without a review (`--force`
+to override) and `raf check` reports visible lots finished after the `uxSince`
+day without one. An empty verdict is refused, and one left empty or blank by hand
+in the YAML counts as no review. Plans without `uxSince` are not affected.
+
+## Code review
+
+```sh
+raf review enable                  # from today, a lot with commits needs a code review before done
+raf commits L4                     # what there is to review: the commits the gate counts for the lot
+raf review L4 "compliant after 2 fixes"   # record the verdict (from the code-reviewer agent)
+```
+
+The counterpart of the UX review, off by default. With the rule on, `raf done`
+refuses a lot that has at least one commit citing it and no recorded verdict
+(`--force` to override), and `raf check` reports such lots finished after the
+`reviewSince` day. A lot with no commit has nothing to review; neither does a
+lot whose only commits touch plan files alone (the plan, a file listed under
+`plan.files`, or the QA expectations file), are version commits (see [Releasing](releasing.md#releasing)), predate the plan's `since` or match an `ignore:` pattern — `raf commits <id>` prints exactly the counted set.
+
+The verdict is tied to what was reviewed: `raf review` stores it on the lot with
+the sha of the lot's latest counted commit (`review: { date, verdict, commit }`,
+`commit: null` when the lot had none). A counted commit made after that one
+makes the review stale: `raf done` refuses (`--force` to override), and
+`raf check` reports a finished lot, until the lot is reviewed again and
+`raf review` is rerun. A verdict
+written by hand without a `commit` field is not checked for staleness. An empty
+verdict is refused, and one left empty or blank by hand in the YAML counts as no
+review. Plans without `reviewSince` are not affected.
+
+A lot that works in neighbouring repositories (`repos:`, see [orchestrate](orchestrate.md#a-lot-whose-work-is-in-a-neighbouring-repository))
+has its verdict tied to each of them: `raf review` also stores, under `repos`, the sha of the latest counted commit of the
+lot in each neighbour (the one `raf commits` lists last: it cites the lot, falls within the lot's period and contains the `cite:` string if any) (`review: { date, verdict, commit, repos: { ../aetherwx-gitops: <sha> } }`, `null` when a
+neighbour has none), and refuses to record when a listed repository cannot be read. `raf check` does not audit the
+neighbours: their staleness is not checked, only the project's own commits are.
+
+## Documentation that follows the code
+
+A stale README misleads. `cadence.yaml` can declare which documents must follow which code:
+
+```yaml
+docs:
+  sync:
+    - paths: [src/**, bin/*.js]        # what changes…
+      docs: [README.md, docs/usage.md]  # …must change one of these, in the same lot
+    - paths: [templates/]
+      docs: [CLAUDE.md]
+    - paths: [frontend/src/**, '!**/*.test.tsx']   # a pattern starting with ! leaves files out
+      docs: [README.md]
+  since: 2026-10-09                    # optional: also audit lots finished on or after this day
+```
+
+A pattern is an exact path, with `*` (inside a folder), `**` (across folders), `?`, or a trailing `/` for
+a whole folder. `raf check` takes the **work commits** of every lot in progress (plan-only commits and
+version commits do not count — so a "What's new" line written in the version commit is not documentation; a lot finished on or after `docs.since` is audited too) and, for each pair, reports the lot when
+those commits touch `paths` without any of them touching a file of `docs`:
+
+```
+✗ L7 : documentation en retard — src/a.ts, src/b.ts sans toucher README.md ou docs/usage.md (docs.sync)
+```
+
+It counts as drift: exit code 1, shown in the `dérive` column of `cadence lead tour`, and the review
+brief of `cadence orchestrate` (`review` and `review-small`) carries the list the program computed,
+to be reported as one **major** finding per line — a stale document is not left to the reviewer's
+memory of a sentence. Touching a document is what the program checks; whether its text is true is
+still the review's reading. The commits of neighbouring repositories (`repos:`) are not audited.
+
+### An article elsewhere that follows the delivery
+
+A case study that lives in a neighbouring repository (the project's article on a showcase site) goes stale
+the same way. `docs.articles` names it:
+
+```yaml
+docs:
+  articles:
+    - repo: ../claude-code-codex          # neighbouring repository, relative to the project
+      file: src/pages/cas/demo.md         # the article in it
+      name: demo                          # optional: the name in the lot title (default: the plan's project)
+```
+
+After a **green** `cadence deliver`, for the lots it lists as delivered **that have a public title** (`public:`, or
+the title of their Nouveautés entry), cadence opens in this repository's plan the lot
+`Article demo à rafraîchir` (todo, estimate 0.5, `repos: [{ path: ../claude-code-codex, cite: demo }]`), with a note
+that quotes the delivery, the public titles delivered, the article and the **sections to read again**: the headings
+(`#` lines, or `<h1>`…`<h6>` of an Astro page) that share a word of five letters or more with a delivered title,
+else all the `##` headings. The lot is then played like any other, in an ordinary wave (`cadence orchestrate`: an
+implementer rewrites the article in the neighbouring repository, the review checks it against the note). If a lot
+of that title is still open, it receives a note instead of a duplicate. Two entries with the same name (the same
+project told in two neighbouring repositories) share one lot, which declares both repositories in `repos:`. Internal lots (no public title) open nothing;
+a red delivery opens nothing; `cadence deliver --dry-run` announces the articles. The plan is written but **not
+committed** (`deliver` never commits): the line `article à rafraîchir : L9 …` says so. With a plan kept by another
+tool (read-only), the same line carries the instruction to open the lot with that tool. This replaces the manual
+`sync-site-docs` skill.
+
+## QA review
+
+No gate and no command here: the QA review comes **after** a delivery, and
+`raf done` does not wait for it. It follows any delivery that changes what a
+page shows or what it is served (screen, API, data source, configuration of
+either) — in practice every delivery except docs-, plan- or tests-only ones: a
+backend-only lot can empty a page without touching a screen, and the agent then
+walks the pages that call the changed endpoints. It also walks the pages that consume the services the lot changed; when the diff changes no route and no screen, or cannot be linked to pages, it walks every page and says so. The `qa-reviewer` agent
+opens each page of the running app in a real browser and judges it from the
+user's side. A page can be empty while everything else is green — no code
+changed, a data source went down upstream, the unit tests replace the network,
+`/api/health` answers ok, and the "nothing found" on screen is the message the
+code was written to show.
+
+The agent cannot tell such an empty state from a normal one by itself: the
+project says what each page must show, in `docs/qa/expectations.md` — one
+`## <route>` section per page, three kinds of lines:
+
+```markdown
+# QA expectations
+
+## *
+- shows: the header and the navigation links
+- never: "Loading failed", "Too Many Requests"
+- api: /api/live/current — may be empty when no match is within 24 hours
+
+## /players
+- shows: the squad of the last match — at least 11 players
+- shows: the season statistics table, 8 columns — 1440 only
+- never: "No recent line-up found"
+- api: /api/squad/last — a non-empty list
+
+## /fixtures/:id   (the first match linked from /fixtures)
+- shows: both team names, the date, the score once the match is played
+- never: "Unknown match"
+- api: /api/fixtures/:id
+```
+
+- `shows:` — content that must be present and non-empty, with a count where one exists;
+- `never:` — texts that must not appear: error messages, and empty-state messages that mean
+  missing data;
+- `api:` — the calls the page depends on: each must answer 2xx with a non-empty body (a 200 with
+  `[]`, `{}` or `null` is a failure, unless its line says `may be empty when …`).
+
+An optional `## *` section holds what every page must show, never show and call. A line may end
+with a condition in plain words, which the agent honours: `may be empty when …`, `1440 only`,
+`390 only` (a line without a width holds at both). Content hidden on the phone by design is not a
+defect unless a `shows:` line requires it at 390; content pushed outside the visible area (it
+needs a sideways scroll) is reported as suspect and handed to `ux-reviewer` in one line.
+
+The rest is free text, written for a reader: a line can be repeated, and a route with a parameter
+names a real value to visit or says where to find one. The file can live elsewhere:
+
+```yaml
+# cadence.yaml
+qa:
+  expectations: docs/quality/pages.md
+```
+
+The agent reads that key, and so does `raf check`: a commit touching only that file is plan upkeep (no lot to cite, see above). Without an expectations file the agent walks
+the routes it discovers and still runs its universal checks: an error shown, a failed API call
+whose content is missing on screen, a broken or missing content image are defects with or without a
+file; an empty 2xx body, like whatever else would need an expectation to judge, is suspect at most
+(it may be a normal absence). For a route with a
+parameter, it finds a real value in the app's links or its API responses and says how it built the
+URL. The agent then returns a draft for you to correct — it never writes the file itself.