fdeops 3.7.4 → 3.7.7

package/README.md

@@ -17,7 +17,7 @@ The **second brain for Forward Deployed Engineers** - engineers embedded at a cl
              written as a side effect of the work
 ```
 
-Describe your situation - `@fde` routes to the phase, runs the method, and every artifact lands in that shared memory. Nothing to maintain by hand.
+Describe your situation - `@fde` routes to the right method and writes the matching `.fde/` artifact. Phase methods (land → close) live in the skill; the CLI owns scan, memory, and receipts. You still confirm judgment — the fieldbook does not maintain itself without you.
 
 ---
 
@@ -86,7 +86,7 @@ Not ready to install? `npx fdeops scan` runs on any repo you can read - day-1 re
 
 ## The week
 
-This is the actual habit, not the 35 skills:
+This is the actual habit — the high-frequency loop, not the full skill matrix:
 
 - **Monday morning** - open your agent, context loads, you're not re-explaining anything
 - **After a meeting** - `fde debrief` turns raw notes into dated decisions, risks, and signals
@@ -148,15 +148,17 @@ fde debrief notes.md              # route meeting notes into memory (also reads
 fde log decision "descope agreed with Kowalczyk"
 fde log contact "Denise gone quiet" --signal amber
 fde receipts <term>               # dated search; no hit = a gap in the record, not proof of absence
-fde status                        # portfolio triage across all clients (red > amber > green)
-fde dashboard                     # render every engagement into one offline HTML fieldbook
+fde status                        # current engagement triage (add --all for every client)
+fde dashboard                     # current engagement fieldbook (add --all for every client)
 ```
 
+Optional: `export FDEOPS_ENGAGEMENTS_ROOT=~/path/to/engagements` to isolate init/status/dashboard from the default `~/fde-engagements`.
+
 The latest dated `[signal:...]` token per stakeholder drives the trust column in `status` and `dashboard`; signals older than 21 days show as stale.
 
 <p align="center"><img src="media/terminal-demo.svg" alt="fde CLI - status, scan, dashboard" width="720"/></p>
 
-`fde dashboard (FieldBook)` renders every engagement into one offline HTML fieldbook - engagements sorted by trust, next action and open risks per client, one glance to know where to start:
+`fde dashboard` (FieldBook) renders the **current** engagement by default. Pass `--all` for every client sorted by trust:
 
 <p align="center"><img width="1336" height="624" alt="Screenshot 2026-07-08 at 12 45 07" src="https://github.com/user-attachments/assets/5683614c-7730-4a3a-860d-185053a377eb" /></p>
 

package/bin/check.js

@@ -32,6 +32,7 @@ const requiredTemplates = [
   'decisions.md',
   'risks.md',
   'delivery.md',
+  'assumptions.md',
 ]
 
 for (const f of requiredTemplates) {
@@ -180,7 +181,7 @@ else ok('docs/schema.md')
 if (!fs.existsSync(path.join(root, 'SECURITY.md'))) fail('SECURITY.md missing')
 else ok('SECURITY.md')
 
-const exampleFiles = ['reality.md', 'decisions.md', 'delivery.md', 'stakeholders.md']
+const exampleFiles = ['reality.md', 'decisions.md', 'delivery.md', 'stakeholders.md', 'assumptions.md']
 for (const f of exampleFiles) {
   const p = path.join(root, 'examples', 'garvey-payments', '.fde', f)
   if (!fs.existsSync(p)) fail(`examples/garvey-payments/.fde/${f} missing`)
@@ -220,12 +221,15 @@ for (const h of ['session-start', 'session-stop', 'pre-compact']) {
 }
 ok('hook exec bits')
 
-// registry-aware hooks: `fde resume --init` binds via ~/fde-engagements/.registry,
-// so every hook must consult it or registry-bound users get zero auto-capture
+// registry-aware hooks: `fde resume --init` binds via <root>/.registry, so every
+// hook must consult it or registry-bound users get zero auto-capture. The root
+// is FDEOPS_ENGAGEMENTS_ROOT with a ~/fde-engagements default - hooks must use
+// the env-aware root (CLI/hook parity), not a hardcoded home path.
 for (const h of ['session-start', 'session-stop', 'pre-compact']) {
   const body = read('hooks/' + h)
-  if (!body.includes('fde-engagements/.registry')) fail(`hooks/${h} must consult the workspace registry`)
+  if (!/\.registry/.test(body)) fail(`hooks/${h} must consult the workspace registry`)
   if (!body.includes('registry_engagement_dir')) fail(`hooks/${h} missing registry_engagement_dir`)
+  if (!body.includes('FDEOPS_ENGAGEMENTS_ROOT')) fail(`hooks/${h} must honor FDEOPS_ENGAGEMENTS_ROOT (CLI/hook root parity)`)
 }
 ok('hooks registry-aware')
 

package/bin/fde.js

@@ -16,8 +16,8 @@
  *   fde debrief [file]      meeting notes → structured memory (stdin if no file)
  *   fde receipts <term>     "what did we agree?" - search memory with dates
  *   fde capture             session-end snapshot → context.md (hooks use this)
- *   fde status              portfolio across ~/fde-engagements (red/amber/green)
- *   fde dashboard           render every engagement into one local fieldbook.html
+ *   fde status [--all]      current engagement (default) or full portfolio (--all)
+ *   fde dashboard [--all]   current engagement fieldbook (default) or all (--all)
  */
 const fs = require('fs')
 const path = require('path')
@@ -25,8 +25,12 @@ const os = require('os')
 const { execSync, execFileSync } = require('child_process')
 
 const HOME = os.homedir()
-const ENGAGEMENTS_ROOT = path.join(HOME, 'fde-engagements')
+// FDEOPS_ENGAGEMENTS_ROOT isolates init/status/dashboard (and the registry) for
+// dogfood/simulations. Default remains ~/fde-engagements.
+const ENGAGEMENTS_ROOT = ((process.env.FDEOPS_ENGAGEMENTS_ROOT || '').trim().replace(/^~/, HOME))
+  || path.join(HOME, 'fde-engagements')
 const REGISTRY = path.join(ENGAGEMENTS_ROOT, '.registry')
+const DEBRIEF_MAX_BYTES = 256 * 1024
 const CODE_EXT = ['.js', '.ts', '.tsx', '.jsx', '.py', '.java', '.go', '.rb', '.cs', '.php']
 const CONF_EXT = CODE_EXT.concat(['.env', '.yaml', '.yml', '.json'])
 // one routing table for structured appends - cmdLog and cmdDebrief share it
@@ -584,7 +588,12 @@ function resumeView(md) {
   // matches the bash hook's `wc -l` and the two bounded views stay byte-aligned.
   if (lines.length > 0 && lines[lines.length - 1] === '') lines.pop()
   if (lines.length <= 160) return md
-  let headEnd = lines.findIndex(l => l.includes('fdeops auto-capture'))
+  // Anchor on the "## Session end" heading, NOT the "<!-- fdeops auto-capture -->"
+  // comment: this text is read via readClean (stripPrivate strips HTML comments),
+  // so the comment is gone by the time we get here. The heading is written on the
+  // very next line by cmdCapture and the session-stop hook and survives redaction.
+  // The bash bounded_context() anchors on the same heading - keep them identical.
+  let headEnd = lines.findIndex(l => /^##\s+Session end\b/.test(l.trim()))
   if (headEnd === -1) headEnd = 120
   headEnd = Math.min(headEnd, 120)
   const tailStart = Math.max(headEnd, lines.length - 40)
@@ -634,10 +643,26 @@ function cmdDebrief(args) {
   if (!eng) { console.error('no engagement - run: fde resume --init <name>'); process.exit(2) }
   let input = ''
   if (args[0]) {
-    try { input = fs.readFileSync(args[0].replace(/^~/, HOME), 'utf8') }
-    catch (_) { console.error(`cannot read ${args[0]}`); process.exit(1) }
+    const notesPath = args[0].replace(/^~/, HOME)
+    let st
+    try { st = fs.statSync(notesPath) } catch (_) { console.error(`cannot read ${args[0]}`); process.exit(1) }
+    if (st.size > DEBRIEF_MAX_BYTES) {
+      console.error(`debrief refused: ${args[0]} is ${st.size} bytes (max ${DEBRIEF_MAX_BYTES}). Split the notes or paste the relevant section.`)
+      process.exit(1)
+    }
+    let buf
+    try { buf = fs.readFileSync(notesPath) } catch (_) { console.error(`cannot read ${args[0]}`); process.exit(1) }
+    if (buf.includes(0)) {
+      console.error(`debrief refused: ${args[0]} looks binary (null bytes). Paste text notes only.`)
+      process.exit(1)
+    }
+    input = buf.toString('utf8')
   } else {
     try { input = fs.readFileSync(0, 'utf8') } catch (_) {} // stdin until EOF
+    if (Buffer.byteLength(input, 'utf8') > DEBRIEF_MAX_BYTES) {
+      console.error(`debrief refused: stdin is over ${DEBRIEF_MAX_BYTES} bytes. Split the notes.`)
+      process.exit(1)
+    }
   }
   const d = new Date()
   const date = d.toISOString().slice(0, 10)
@@ -681,7 +706,7 @@ function cmdReceipts(args) {
   // same list let an FDE cite a sales promise as a receipt - so they get a
   // separate, clearly-labelled section that is never mistaken for the record.
   const AGREEMENTS = ['decisions.md', 'delivery.md', 'success.md', 'risks.md', 'stakeholders.md']
-  const CLAIMS = ['brief.md', 'reality.md', 'context.md']
+  const CLAIMS = ['brief.md', 'assumptions.md', 'reality.md', 'context.md']
   const collect = files => {
     const hits = []
     for (const f of files) {
@@ -735,26 +760,42 @@ function cmdCapture() {
   try { fs.appendFileSync(path.join(eng, 'context.md'), block) } catch (_) {}
 }
 
-function cmdStatus() {
+function engagementSlugFromPath(eng) {
+  return path.basename(path.dirname(eng))
+}
+
+function cmdStatus(args) {
+  const all = args.includes('--all')
   if (!fs.existsSync(ENGAGEMENTS_ROOT)) { console.log('no engagements yet - fde resume --init <name>'); return }
   const rows = []
-  for (const d of fs.readdirSync(ENGAGEMENTS_ROOT)) {
-    if (d.startsWith('.')) continue
-    const eng = path.join(ENGAGEMENTS_ROOT, d, '.fde')
-    if (!fs.existsSync(eng)) continue
+  if (all) {
+    for (const d of fs.readdirSync(ENGAGEMENTS_ROOT)) {
+      if (d.startsWith('.')) continue
+      const eng = path.join(ENGAGEMENTS_ROOT, d, '.fde')
+      if (!fs.existsSync(eng)) continue
+      const s = computeSignals(eng)
+      rows.push({ name: d, phase: s.phase, trust: s.trust, signalAge: s.signalAge, stale: s.stale, updated: s.updated, topRisk: s.topRisk.slice(0, 60) })
+    }
+  } else {
+    const eng = resolveEngagement()
+    if (!eng) {
+      console.error('no engagement bound to this workspace.\nrun: fde resume --init <name>   or   fde status --all')
+      process.exit(2)
+    }
     const s = computeSignals(eng)
-    rows.push({ name: d, phase: s.phase, trust: s.trust, signalAge: s.signalAge, stale: s.stale, updated: s.updated, topRisk: s.topRisk.slice(0, 60) })
+    rows.push({ name: engagementSlugFromPath(eng), phase: s.phase, trust: s.trust, signalAge: s.signalAge, stale: s.stale, updated: s.updated, topRisk: s.topRisk.slice(0, 60) })
   }
   if (!rows.length) { console.log('no engagements yet'); return }
   const order = { RED: 0, amber: 1, green: 2 }
   rows.sort((a, b) => order[a.trust] - order[b.trust])
-  console.log('FDE PORTFOLIO - trust-first triage (heuristic: red > amber > green)\n')
+  console.log((all ? 'FDE PORTFOLIO' : 'FDE STATUS') + ' - trust-first triage (heuristic: red > amber > green)\n')
   for (const r of rows) {
     // "amber?" = structured signal went stale (>21d) - reconfirm before trusting it
     const label = r.trust + (r.stale ? '?' : '')
     const sig = r.signalAge != null ? `signal ${r.signalAge}d old${r.stale ? ' (STALE - reconfirm)' : ''}  ` : ''
     console.log(`  [${label.padEnd(6)}] ${r.name.padEnd(24)} phase:${r.phase.padEnd(10)} updated:${r.updated.padEnd(8)} ${sig}${r.topRisk}`)
   }
+  if (!all) console.log('\n(current engagement only - pass --all for the full portfolio)')
   console.log('\ntrust: latest [signal:x] token in stakeholders.md wins (fde log contact --signal, fde debrief); keyword heuristic only when none exists - verify before acting.')
 }
 
@@ -839,8 +880,12 @@ function hasRealContent(md) {
   return txt.length > 0
 }
 
-function gatherEngagements() {
+function gatherEngagements(opts = {}) {
   const list = []
+  if (opts.only) {
+    list.push({ name: engagementSlugFromPath(opts.only), dir: opts.only, signals: computeSignals(opts.only) })
+    return list
+  }
   if (!fs.existsSync(ENGAGEMENTS_ROOT)) return list
   for (const d of fs.readdirSync(ENGAGEMENTS_ROOT).sort()) {
     if (d.startsWith('.')) continue
@@ -1364,11 +1409,22 @@ function paletteItemsHtml(ordered) {
 }
 
 function cmdDashboard(args) {
+  const all = args.includes('--all')
   const outIdx = args.indexOf('--out')
   const outPath = outIdx !== -1 && args[outIdx + 1]
     ? path.resolve(args[outIdx + 1].replace(/^~/, HOME))
-    : path.join(ENGAGEMENTS_ROOT, 'fieldbook.html')
-  const engagements = gatherEngagements()
+    : path.join(ENGAGEMENTS_ROOT, all ? 'fieldbook.html' : 'fieldbook-current.html')
+  let engagements
+  if (all) {
+    engagements = gatherEngagements()
+  } else {
+    const eng = resolveEngagement()
+    if (!eng) {
+      console.error('no engagement bound to this workspace.\nrun: fde resume --init <name>   or   fde dashboard --all')
+      process.exit(2)
+    }
+    engagements = gatherEngagements({ only: eng })
+  }
   const counts = { green: 0, amber: 0, RED: 0 }
   engagements.forEach(e => { counts[e.signals.trust]++ })
   const today = formatToday(new Date())
@@ -1506,7 +1562,7 @@ switch (cmd) {
   case 'debrief': cmdDebrief(args); break
   case 'receipts': cmdReceipts(args); break
   case 'capture': cmdCapture(); break
-  case 'status': cmdStatus(); break
+  case 'status': cmdStatus(args); break
   case 'dashboard': cmdDashboard(args); break
   default:
     console.log(`fde - deterministic core of fdeops
@@ -1519,6 +1575,7 @@ switch (cmd) {
   fde debrief [file]       meeting notes → memory: decision:/risk:/delivery:/contact: lines route, rest → context.md (stdin if no file; --dry-run previews)
   fde receipts <term>      "what did we agree?" with dates
   fde capture              session-end memory snapshot (hooks use this)
-  fde status               portfolio across all engagements
-  fde dashboard            render every engagement into one local fieldbook.html`)
+  fde status [--all]       current engagement status (pass --all for full portfolio)
+  fde dashboard [--all]    current engagement fieldbook (pass --all for every client)
+  env FDEOPS_ENGAGEMENTS_ROOT  override ~/fde-engagements (init/status/dashboard/registry)`)
 }

package/hooks/pre-compact

@@ -16,7 +16,11 @@ resolve_engagement_dir() {
 # Lines are "<workspace-path> <slug>": the path may contain spaces, the slug
 # never does, so split on the LAST space (same as the JS lastIndexOf parse).
 registry_engagement_dir() {
-  local reg="$HOME/fde-engagements/.registry" slug
+  # FDEOPS_ENGAGEMENTS_ROOT mirrors ENGAGEMENTS_ROOT in bin/fde.js - the CLI and
+  # hooks MUST agree on the root or an isolated setup gets split memory.
+  local root="${FDEOPS_ENGAGEMENTS_ROOT:-$HOME/fde-engagements}"
+  root="${root/#\~/$HOME}"
+  local reg="$root/.registry" slug
   [ -f "$reg" ] || return 1
   slug=$(awk 'BEGIN{ws=ENVIRON["PWD"]; best=-1}
     { i = match($0, / [^ ]*$/)
@@ -28,7 +32,7 @@ registry_engagement_dir() {
       } }
     END { if (best >= 0) print slug }' "$reg" 2>/dev/null)
   [ -z "$slug" ] && return 1
-  [ -d "$HOME/fde-engagements/$slug/.fde" ] && printf '%s\n' "$HOME/fde-engagements/$slug/.fde" && return 0
+  [ -d "$root/$slug/.fde" ] && printf '%s\n' "$root/$slug/.fde" && return 0
   return 1
 }
 

package/hooks/session-start

@@ -28,7 +28,11 @@ resolve_engagement_dir() {
 # Lines are "<workspace-path> <slug>": the path may contain spaces, the slug
 # never does, so split on the LAST space (same as the JS lastIndexOf parse).
 registry_engagement_dir() {
-  local reg="$HOME/fde-engagements/.registry" slug
+  # FDEOPS_ENGAGEMENTS_ROOT mirrors ENGAGEMENTS_ROOT in bin/fde.js - the CLI and
+  # hooks MUST agree on the root or an isolated setup gets split memory.
+  local root="${FDEOPS_ENGAGEMENTS_ROOT:-$HOME/fde-engagements}"
+  root="${root/#\~/$HOME}"
+  local reg="$root/.registry" slug
   [ -f "$reg" ] || return 1
   slug=$(awk 'BEGIN{ws=ENVIRON["PWD"]; best=-1}
     { i = match($0, / [^ ]*$/)
@@ -40,7 +44,7 @@ registry_engagement_dir() {
       } }
     END { if (best >= 0) print slug }' "$reg" 2>/dev/null)
   [ -z "$slug" ] && return 1
-  [ -d "$HOME/fde-engagements/$slug/.fde" ] && printf '%s\n' "$HOME/fde-engagements/$slug/.fde" && return 0
+  [ -d "$root/$slug/.fde" ] && printf '%s\n' "$root/$slug/.fde" && return 0
   return 1
 }
 
@@ -122,7 +126,10 @@ bounded_context() {
   total=$(wc -l < "$f" 2>/dev/null | tr -d ' ')
   [ -z "$total" ] && { cat "$f"; return; }
   if [ "$total" -le 160 ]; then cat "$f"; return; fi
-  head_end=$(grep -n -m1 'fdeops auto-capture' "$f" 2>/dev/null | cut -d: -f1)
+  # Anchor on the "## Session end" heading, matching resumeView() in bin/fde.js.
+  # The JS path reads via readClean (strips HTML comments), so both sides must
+  # anchor on a marker that survives redaction - the heading, not the comment.
+  head_end=$(grep -n -m1 '^## Session end' "$f" 2>/dev/null | cut -d: -f1)
   if [ -n "$head_end" ]; then head_end=$((head_end - 1)); else head_end=120; fi
   [ "$head_end" -gt 120 ] && head_end=120
   [ "$head_end" -lt 0 ] && head_end=0

package/hooks/session-stop

@@ -24,7 +24,11 @@ resolve_engagement_dir() {
 # Lines are "<workspace-path> <slug>": the path may contain spaces, the slug
 # never does, so split on the LAST space (same as the JS lastIndexOf parse).
 registry_engagement_dir() {
-  local reg="$HOME/fde-engagements/.registry" slug
+  # FDEOPS_ENGAGEMENTS_ROOT mirrors ENGAGEMENTS_ROOT in bin/fde.js - the CLI and
+  # hooks MUST agree on the root or an isolated setup gets split memory.
+  local root="${FDEOPS_ENGAGEMENTS_ROOT:-$HOME/fde-engagements}"
+  root="${root/#\~/$HOME}"
+  local reg="$root/.registry" slug
   [ -f "$reg" ] || return 1
   slug=$(awk 'BEGIN{ws=ENVIRON["PWD"]; best=-1}
     { i = match($0, / [^ ]*$/)
@@ -36,7 +40,7 @@ registry_engagement_dir() {
       } }
     END { if (best >= 0) print slug }' "$reg" 2>/dev/null)
   [ -z "$slug" ] && return 1
-  [ -d "$HOME/fde-engagements/$slug/.fde" ] && printf '%s\n' "$HOME/fde-engagements/$slug/.fde" && return 0
+  [ -d "$root/$slug/.fde" ] && printf '%s\n' "$root/$slug/.fde" && return 0
   return 1
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fdeops",
-  "version": "3.7.4",
+  "version": "3.7.7",
   "description": "Field kit for engineers embedded in client work - a real CLI (recon, memory, portfolio), one @fde skill with field judgment on top, and hooks that make it automatic. Claude Code plugin and any agent that loads skills.",
   "bin": {
     "fdeops": "bin/install.js",

package/skills/fde/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: fde
-description: The second brain for Forward Deployed Engineers. 35 skills across 6 domains - from first meeting to final handoff. Tell it your situation, it routes to the right skill, does the work, and the engagement memory writes itself.
+description: Second brain for Forward Deployed Engineers. One @fde router over field methods plus a local CLI for scan, memory, and receipts. Tell it your situation — it routes, does the work, and writes the engagement fieldbook.
 ---
 
 # @fde
@@ -14,7 +14,7 @@ When this skill says "ask the FDE," it means the human. When it says "write to `
 
 ## Purpose
 
-The single entry point for an entire client engagement - 35 skills across 6 domains covering the full FDE lifecycle. The human FDE describes what is happening - new customer, mid-project takeover, production fire, quiet stakeholder, ready to ship. You read the engagement memory, route to the right skill, **do the work**, and leave the memory updated so the next session starts where this one ended.
+The single entry point for an entire client engagement. Field methods cover the FDE lifecycle (land through close, plus daily verbs and overlays). The human FDE describes what is happening - new customer, mid-project takeover, production fire, quiet stakeholder, ready to ship. You read the engagement memory, route to the right method, **do the work**, and leave the memory updated so the next session starts where this one ended.
 
 You are not an advisor reading tips aloud. Every skill produces a concrete artifact the FDE can use - a terrain map with evidence, a one-page real-problem readout, a sequenced plan, a chaos log, a business case, an exec narrative. The artifact is the deliverable AND the memory.
 
@@ -153,7 +153,7 @@ After updating `.fde/` artifacts, suggest the ONE next move that accelerates the
 
 > "Brief written. You don't have repo access yet - want me to draft the request or are you handling that?"
 
-## Routing - 6 domains, 35 skills
+## Routing - 6 domains
 
 Route on what you hear, then **read the skill reference from this skill's `references/` directory and follow its method**. Do not improvise from memory - the method is the product.
 

package/skills/fde/references/assumption-audit.md

@@ -52,21 +52,25 @@ Evidence first, then the question. Let them reach the conclusion.
 
 ## Artifact
 
-**`reality.md`** - append an assumptions section:
+**`assumptions.md`** - this IS the register (create if land did not). Keep one live table; do not only bury results in `reality.md`:
+
 ```markdown
-## Assumptions audited - <date>
-| # | Assumption | Classification | Validation | Result | Impact |
-|---|-----------|---------------|------------|--------|--------|
-| 1 | API is the bottleneck | CRITICAL | p95 instrumentation | DISPROVED - 80% DB | Approach changes from API rewrite to query optimisation |
-| 2 | Team will adopt new tool | LOAD-BEARING | 3 individual interviews | CONFIRMED - 2/3 enthusiastic | Proceed with adoption plan |
-| 3 | Data clean enough for ML | CRITICAL | 200-record sample | PARTIAL - 12% null rate on key field | Data cleaning task added to plan |
+| # | Assumption | Blast radius | How we test | Status | Evidence |
+|---|------------|--------------|-------------|--------|----------|
+| 1 | API is the bottleneck | CRITICAL | p95 instrumentation 24h | DISPROVED | 80% wait in DB layer (Day N) |
+| 2 | Team will adopt new tool | LOAD-BEARING | 3 individual interviews | CONFIRMED | 2/3 describe a use case unprompted |
+| 3 | Data clean enough for ML | CRITICAL | 200-record sample | PARTIAL → OPEN follow-up | 12% nulls on key field; cleaning task added |
 ```
 
-**`decisions.md`** - if an assumption was disproved and the approach changed: what shifted, why, the evidence.
+Status values: `OPEN` · `TESTING` · `CONFIRMED` · `DISPROVED` · `PARKED`. A CRITICAL row still `OPEN` blocks plan.
+
+**`reality.md`** - short pointer only: which assumptions changed the approach and the implication for build.
+
+**`decisions.md`** - if an assumption was disproved and the approach changed: what shifted, why, the evidence, same day.
 
 ## Checkpoint
 
-Tell the FDE: how many assumptions extracted, how many critical, which ones were tested, which changed the direction. If a critical assumption is disproved: recommend the next move (rescope, pivot, or the conversation with the sponsor) before the FDE asks.
+Tell the FDE: how many assumptions extracted, how many critical, which ones were tested, which changed the direction. If a critical assumption is disproved: recommend the next move (rescope, pivot, or the conversation with the sponsor) before the FDE asks. If any CRITICAL remains OPEN: do not route to plan.
 
 ## Principles
 

package/skills/fde/references/build.md

@@ -127,7 +127,7 @@ The FDE's job is to make themselves replaceable. Not at handoff - every day. A c
 
 - **`decisions.md`** - each significant choice: what, alternatives considered, why this one. For non-trivial architecture decisions, present three options to the FDE (safe / pragmatic / aggressive) with costs and a recommendation - three options is a real decision; one option is a request for trust. Integration contracts go here too.
 - **`risks.md`** - new risks discovered while building.
-- **`delivery.md`** - what shipped, in business terms (time saved, failures prevented), and how to roll back. This is the value log the dashboard and close read.
+- **`delivery.md`** - append a **value ledger** row for every ship: Date | Slice | Promised | Measured | Evidence | Rollback. "Measured" may be `pending` until the pulse exists - never skip the promised column. Narrative under Shipped is optional color; the ledger is the record status and close read.
 
 ## Checkpoint
 

package/skills/fde/references/discover.md

@@ -154,6 +154,8 @@ Score every candidate use case before anything gets prototyped:
 
 Every line carries its evidence. `(churn: 47/90d)` `(ops lead, Day 5)` `(stated, unverified)`.
 
+**`assumptions.md`** - update statuses from what discovery proved or disproved. Seed any new OPEN assumptions the brief never named. CRITICAL + OPEN must be named in the checkpoint.
+
 ## Checkpoint (before any build)
 
 Present to the FDE, four things, one paragraph each - no padding:

package/skills/fde/references/initiative-triage.md

@@ -61,7 +61,24 @@ Notice: every stakeholder's initiative is P0 or P1. That's the problem this skil
 
 ## Artifact
 
-**`decisions.md`** - the triage table with scores, lanes, and the commitment statement. Dated. Referenced by plan and status.
+**`decisions.md`** - the triage table with scores, lanes, **and an explicit Kill / Later commitment**. Dated. Referenced by plan and status.
+
+Required closing block (plan will not treat triage as done without it):
+
+```markdown
+## Triage - <date>
+### Now (max 3)
+| # | Initiative | Score | Why now |
+...
+### Next
+...
+### Kill / defer (not this phase)
+| Initiative | Why not now | Who accepted |
+|------------|-------------|--------------|
+| ... | ... | <name, date> |
+
+Commitment: we ship only Now. Additions require a removal.
+```
 
 **`reality.md`** - if triage revealed that the engagement scope is larger than the timeline supports, update the assessment.
 

package/skills/fde/references/land.md

@@ -72,11 +72,19 @@ Before the end of day 1, ship one visible thing: a small bug fix, a cleanup the
 
 **`trust-profile.md`** - sacred data (`<private>` tagged), fears heard, AI policy, approval chain. Sensitive: never loaded for status reads, never into subagent prompts.
 
-One falsifiable hypothesis about the real problem goes at the bottom of `brief.md` - discover will test it.
+**`assumptions.md`** - seed every unverified claim from the brief (and the day-1 hypothesis) as rows with blast radius CRITICAL / LOAD-BEARING / CONVENIENCE and status `OPEN`. Do not wait for assumption-audit - land makes the register exist. Example:
+
+```markdown
+| # | Assumption | Blast radius | How we test | Status | Evidence |
+|---|------------|--------------|-------------|--------|----------|
+| 1 | <claim from brief> | CRITICAL | <cheapest falsifying test> | OPEN | (stated, unverified) |
+```
+
+One falsifiable hypothesis about the real problem also goes at the bottom of `brief.md` - discover / assumption-audit will test it.
 
 ## Checkpoint
 
-One page back to the FDE: success + sign-off owner, out-of-scope boundary, sacred data, stakeholder map with veto power, AI posture, the hypothesis. If it doesn't fit one page, the engagement isn't understood yet.
+One page back to the FDE: success + sign-off owner, out-of-scope boundary, sacred data, stakeholder map with veto power, AI posture, the hypothesis, and the top CRITICAL assumptions still OPEN. If it doesn't fit one page, the engagement isn't understood yet.
 
 If remote: trust-building takes ~40% longer - push for a short video call before anything asynchronous.
 
@@ -84,6 +92,6 @@ If remote: trust-building takes ~40% longer - push for a short video call before
 
 - Never start technical work before `success.md` exists.
 - Sacred data never enters AI context. Ever.
-- The brief is a hypothesis; discover confirms it.
+- The brief is a hypothesis; discover confirms it. Seed `assumptions.md` on day one.
 - The passed-over internal team is the best source of truth, not an obstacle.
 - If the customer cannot define success, that is the first problem to solve.

package/skills/fde/references/plan.md

@@ -22,7 +22,7 @@ An FDE plan is not a sprint backlog. The technical sequence is the easy part. Th
 
 ## Method (you do this work)
 
-**0. Lock scope first.** Read `success.md`. If out-of-scope is undefined, define it now with the FDE - a plan on undefined scope accumulates silent commitments.
+**0. Lock scope first.** Read `success.md` and `assumptions.md`. If out-of-scope is undefined, define it now with the FDE - a plan on undefined scope accumulates silent commitments. If any CRITICAL assumption is still `OPEN`, stop and run assumption-audit / discover before sequencing work.
 
 **1. Work backwards from success.** What's the last thing that must be true before done? And before that? That's the dependency chain - not a wish list.
 
@@ -36,24 +36,43 @@ An FDE plan is not a sprint backlog. The technical sequence is the easy part. Th
 
 **6. Stakeholder touchpoints every 2–3 tasks.** "Show progress to <name from stakeholders.md>." Not ceremony: a customer who sees small wins stays bought in; silence gets filled with doubt.
 
+**7. End with a kill list.** Every plan names what you will **not** do this phase. If everything is "later," you have no plan - you have a wish list. Cap **Now** at 3 slices (same discipline as initiative-triage).
+
 **Acceptance criteria gate:** no task moves to build without written happy-path AND unhappy-path criteria. Can't write them = the task isn't understood; the open question goes to the customer **before** the task starts. Vague criteria surface later as scope creep and rework.
 
 ## Artifact
 
 The plan goes to **`decisions.md`** - always. Build reads the plan from `decisions.md`; anywhere else and the build starts blind.
 
+A plan is **not done** until all four blocks exist:
+
 ```markdown
+## Plan - <date>
+### Now (max 3)
 Task N: <outcome, not activity>
 Delivers: <what someone can see/test>
 Accepts: <happy path> / <unhappy path>
 Touches: <files/systems - blast radius declared upfront>
 Risk: <what could go wrong + fallback>
 Verify: <specific check>
+Value promised: <business unit change this slice claims>
+
+### Next
+- ...
+
+### Later
+- ...
+
+### Kill list (explicitly not this phase)
+| Item | Why killed / deferred | Who accepted |
+|------|----------------------|--------------|
+| <rewrite / nice-to-have / political ask> | <evidence> | <name, date> |
 ```
 
+No kill list → not a finished plan. Reopen with the FDE until the deferrals are written.
 ## Checkpoint
 
-Walk the FDE through: sequence + why this order, where the fragile work sits, where the touchpoints land, the acceptance gate on task 1. One question: "Which stakeholder sees the first visible slice, and when?"
+Walk the FDE through: sequence + why this order, where the fragile work sits, where the touchpoints land, the acceptance gate on task 1, and the kill list. One question: "Which stakeholder sees the first visible slice, and when?" Second: "Who accepted what we are not doing?"
 
 ## Method - estimation (when the sponsor asks "how long, how much?")
 
@@ -118,5 +137,6 @@ Never quietly update tasks. Name the reset: update `reality.md` and `success.md`
 - Fragile zones early. Fail fast.
 - Every 2–3 tasks, a stakeholder touchpoint. Trust decays without visibility.
 - No written acceptance criteria, no build.
+- No kill list, no finished plan.
 - Estimates are ranges, not promises. Name the assumptions.
 - Migrations: leaf nodes first, core last. Rollback before cutover.

package/skills/fde/references/status.md

@@ -2,29 +2,51 @@
 
 **Enter when:** the weekly update is due, an exec asks "where are we," or the FDE says "I need to send Dana something." This artifact decides renewals; engineers underinvest in it.
 
-**Read first:** `success.md` (the yardstick), `delivery.md`, `decisions.md`, `risks.md`, `context.md`. Gather the week's facts: `fde receipts` for agreements, `git log --since='7 days ago' --oneline` for shipped work.
+**Read first:** `success.md` (the yardstick), `delivery.md` (value ledger), `decisions.md` (plan + kill list), `assumptions.md` (OPEN criticals), `risks.md`, `context.md`. Gather the week's facts: `fde receipts` for agreements, `git log --since='7 days ago' --oneline` for shipped work.
 
 ## Method (you do this work)
 
-1. **Lead with value in their units** - time saved, errors prevented, revenue protected, risk retired. Never "completed the API endpoint"; always what the endpoint *does for the business*.
-2. **Progress against `success.md`** - the agreed definition of done, not a task list. On / ahead / behind, with the why in one line.
-3. **Bad news first, never buried.** A risk the sponsor learns from your update is managed; a risk they learn from their staff is a trust fire. Each risk: one line + what you're doing about it + what you need from them.
-4. **The ask, explicit.** Access, a decision, an introduction, a sign-off. Updates without asks train sponsors to skim.
-5. **Next week in three bullets.** What they'll see, when, and the next touchpoint.
+**Always draft in SCQA.** One page maximum. No other shape.
 
-One page maximum. Exec voice: no jargon, no hedging, every claim traceable to the memory (`(shipped Tue, delivery.md)`). Draft in the **FDE's voice, for the FDE to send** - never send anything yourself.
+| Block | What to write | Source |
+|-------|---------------|--------|
+| **S — Situation** | Where we are against `success.md`, in their words | success.md, delivery value ledger |
+| **C — Complication** | What changed, what is at risk, or what we learned (bad news first) | risks.md, assumptions DISPROVED/OPEN, stakeholders signal |
+| **Q — Question / Ask** | The one decision or help you need from them | decisions.md, access/sign-off needs |
+| **A — Answer** | What you recommend / what happens next week (≤3 bullets) | plan Now lane, delivery promised→measured |
+
+Then add, still on the same page:
+1. **Value this week** - from the value ledger: promised → measured (or "pending") with evidence citation.
+2. **Kill / defer reminder** - one line from the plan kill list so scope fights stay visible.
+3. **Hostile Q prep** - three questions a skeptical sponsor will ask, with one-line answers from memory.
+
+Exec voice: no jargon, no hedging, every claim traceable (`(shipped Tue, delivery.md)`). Draft in the **FDE's voice, for the FDE to send** - never send anything yourself.
+
+For board / renewal / sponsor's boss (longer pyramid): use `exec-narrative.md`. Do not invent a second weekly format.
 
 ## Artifact
 
-Append the draft to `delivery.md` under `## Status - <date>` (the running record the close phase and dashboard read). Note in `context.md`: status drafted, awaiting FDE review/send.
+Append the draft to `delivery.md` under `## Status - <date>` using the SCQA headings. Note in `context.md`: status drafted, awaiting FDE review/send.
+
+```markdown
+## Status - YYYY-MM-DD
+**S:** ...
+**C:** ...
+**Q:** ...
+**A:** ...
+**Value ledger:** promised … / measured … (evidence)
+**Kill list reminder:** …
+**Hostile Qs:** 1) … 2) … 3) …
+```
 
 ## Checkpoint
 
-Walk the FDE through the two highest-stakes lines - the worst risk and the biggest ask - and confirm the framing matches what the sponsor can hear right now (check `stakeholders.md` signal first: a red-signal sponsor gets a different opening than a green one).
+Walk the FDE through the Complication and the Ask - confirm the framing matches what the sponsor can hear right now (check `stakeholders.md` signal first: a red-signal sponsor gets a different opening than a green one).
 
 ## Principles
 
-- No surprises: anything the sponsor would be angry to learn later goes in this update.
-- Value in their units, progress against the agreed yardstick, one page.
+- SCQA every time. Situation → Complication → Ask → Answer.
+- No surprises: anything the sponsor would be angry to learn later goes in Complication.
+- Value from the ledger, not from ticket theater.
 - An update without an ask is a missed move.
 - You draft; the FDE sends. Their voice, their relationship.

package/templates/.fde/assumptions.md

@@ -0,0 +1,11 @@
+# Assumptions
+
+<!-- Brief claims that are not yet evidence. Land seeds; assumption-audit / discover update. -->
+
+| # | Assumption | Blast radius | How we test | Status | Evidence |
+|---|------------|--------------|-------------|--------|----------|
+| 1 | *(seed from brief - stated, unverified)* | CRITICAL / LOAD-BEARING / CONVENIENCE | | OPEN | |
+
+**Status values:** `OPEN` · `TESTING` · `CONFIRMED` · `DISPROVED` · `PARKED`
+
+**Rule:** a CRITICAL assumption still OPEN blocks plan. DISPROVED → update `reality.md` / `success.md` and log the reset in `decisions.md` the same day.

package/templates/.fde/delivery.md

@@ -1,7 +1,17 @@
 # Delivery log
 
-<!-- Business-visible value, not ticket theater. -->
+<!-- Business-visible value, not ticket theater. Every ship gets a value ledger row. -->
+
+## Value ledger
+
+| Date | Slice | Promised | Measured | Evidence | Rollback |
+|------|-------|----------|----------|----------|----------|
+| | | *(what we said it would change)* | *(what actually changed, or pending)* | *(who/when/metric)* | |
 
 ## Shipped
 
+## Status updates
+
+<!-- Append ## Status - YYYY-MM-DD drafts from @fde status (SCQA). -->
+
 ## Running value