fdeops 5.1.21 → 5.1.23

package/README.md

@@ -53,6 +53,8 @@ Here are the agreed behavior, repository and checks: ...
 
 Each task skill includes the instructions it needs. Use `build` with supplied project context without creating a customer record or installing the coordinator.
 
+Use only the methods the work needs, whether the engagement lasts three days, three weeks or several months. A clear, bounded task can go straight to implementation. Uncertain requirements, dependent teams or production risk may need more discovery and coordination. Reuse the customer’s existing tools and approvals; the skill catalog is not a sequence to complete.
+
 <details>
 <summary>Installation requirements and alternatives</summary>
 

package/bin/fde.js

@@ -1773,21 +1773,33 @@ function looksLikePersonName(s) {
 function signerFromLine(text) {
   const t = String(text || '').replace(/^[-*+]\s+/, '').trim()
   if (!t || /\?|\b(?:not|nobody|unclear|maybe|might|whether|could|should|if|unless|pending|unconfirmed)\b/i.test(t)) return ''
+  // A component/budget/release approver is not the engagement's acceptance
+  // signer. Infer only a bare authority statement or explicit outcome/test
+  // sign-off; leave other scope wording in the original note for agent review.
+  const roleWords = text => text.trim().split(/\s+/).every(word => word.match(ROLE_TOKEN)?.[0] === word)
+  const candidate = (match, who, rolePrefix = false) => {
+    if (!match || !looksLikePersonName(who)) return ''
+    const before = t.slice(0, match.index)
+    const after = t.slice(match.index + match[0].length).replace(/\[source:[^\]]*\]/gi, '').trim()
+    if (before.trim() && (!rolePrefix || !roleWords(before))) return ''
+    if (!/^(?:(?:on\s+)?(?:the\s+)?(?:acceptance tests?|(?:customer |delivered )?outcome))?[.!]?$/i.test(after)) return ''
+    return who.trim()
+  }
   // "Priya (VP Eng) signs off" → Priya. "Finance controller (Helena) signs off" → Helena.
   const titled = t.match(new RegExp('\\b' + SIGNER_NAME + '\\s+\\(' + SIGNER_NAME + '\\)\\s+' + SIGNER_VERB + '\\b'))
   if (titled) {
     const before = titled[1].trim()
     const inside = titled[2].trim()
-    if (looksLikePersonName(before) && ROLE_TOKEN.test(inside)) return before
-    if (looksLikePersonName(inside)) return inside
-    if (looksLikePersonName(before)) return before
+    if (looksLikePersonName(before) && roleWords(inside)) return candidate(titled, before)
+    if (roleWords(before) && looksLikePersonName(inside)) return candidate(titled, inside)
+    return ''
   }
   const paren = t.match(new RegExp('\\(' + SIGNER_NAME + '\\)\\s+' + SIGNER_VERB + '\\b'))
-  if (paren && looksLikePersonName(paren[1])) return paren[1].trim()
+  if (paren && looksLikePersonName(paren[1])) return candidate(paren, paren[1], true)
   const named = t.match(new RegExp('\\b' + SIGNER_NAME + '\\s+' + SIGNER_VERB + '\\b'))
   if (!named) return ''
   const who = named[1].trim()
-  return looksLikePersonName(who) ? who : ''
+  return candidate(named, who)
 }
 
 function setSigner(eng, who) {

package/mcp/fdeops-ingest/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fdeops-ingest-mcp",
-  "version": "5.1.21",
+  "version": "5.1.23",
   "private": true,
   "description": "Thin stdio MCP sink for FDEOps ingest (stage \u2192 propose \u2192 apply). Zero runtime dependencies.",
   "bin": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fdeops",
-  "version": "5.1.21",
+  "version": "5.1.23",
   "description": "Skills for forward deployed engineers across strategy, architecture and engineering. Use individual tasks or @fde coordination; local customer memory supports continuity.",
   "bin": {
     "fdeops": "bin/install.js",

package/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "fdeops",
-  "version": "5.1.21",
+  "version": "5.1.23",
   "description": "Skills for forward deployed engineers across strategy, architecture and engineering. Use individual tasks or @fde coordination; local customer memory supports continuity.",
   "author": {
     "name": "Subash Natarajan",

package/skills/audit/.fde-generated.json

@@ -6,6 +6,6 @@
     "agents/openai.yaml": "3b08e2e6a4149545da08238463955501bc60b7bf628cf4e344e893330590bbde",
     "references/audit.md": "ed32ea78cbccb100742dd838e8cf4cd4b6f33ad44b3de7424fc624670d571dbc",
     "references/discover.md": "f65aa11a539b4dbbed70cfaa94ec2a35595aa9a2d0282790510b933ac9c721ce",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/audit/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/board-memo/.fde-generated.json

@@ -6,6 +6,6 @@
     "agents/openai.yaml": "a3ce2dc79d3732da6c9aa2d45d09541c09c8f7bdf44f34c6603b5dbaf8624095",
     "references/board-memo.md": "44eb3c27f164da63af694591025b3fc96bb23d149c29de400997c1653e3322f8",
     "references/business-case.md": "32e000e8351cd59f9eaad8be40babb276df69948ea4f81e01a4672e47f48cb25",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/board-memo/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/brief/.fde-generated.json

@@ -4,7 +4,7 @@
   "files": {
     "SKILL.md": "5d88b9818951f8a8a44c39ad2b36ccdca74fef5e6ed31e67788b50d3ca1bb006",
     "agents/openai.yaml": "8dc0b43545004419bad49e1d50cd3beb968bbcc24baacdaf7fb7304a5fd03bba",
-    "references/land.md": "87dfffc8e39d35eaf23d510ba7e9913d48e90d2705eb9155ab192d12ea98d18d",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/land.md": "f33f1b9e03a3c23c39ffce925a8f8b956b48a53982f55246752a48a317cb084d",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/brief/references/land.md

@@ -4,6 +4,8 @@
 
 **Read first:** apply [task context](task-context.md), then permitted `context.md` evidence if it exists and the supplied brief. Once the engagement type and AI/access policy are known, inspect the supplied repo/docs relevant to the ask before asking questions they can answer. This is a bounded evidence check, not a full discovery scan.
 
+**Bounded engagement:** A new customer does not automatically require a full landing exercise. For a single-outcome task or simulation of any duration, use the supplied brief to establish the outcome, deadline, permitted inputs, acceptance and next authorized action. If those are clear, route to the working task immediately. If one material gap remains, investigate that gap; do not build a stakeholder map or populate engagement files for their own sake. A simulated stakeholder does not justify invented meetings or approval chains. Keep actual data and release authority checks where they affect the work.
+
 ## Validation gate (confirm understanding, clarify where it elevates)
 
 Before landing, state what you know in 2-3 lines:
@@ -12,7 +14,7 @@ Before landing, state what you know in 2-3 lines:
 
 Then check - probe ONLY if it prevents a bad start:
 
-1. **Engagement speed.** If timeline is unclear → weave it in naturally: "Is this days, weeks, or months? That shapes how much structure we set up now."
+1. **Deadline and scope.** Ask about timing only when it changes the next action: "What result is needed by when?" Use uncertainty, dependencies, risk and access to choose the necessary structure; duration alone does not decide it.
 2. **Existing context.** If `.fde/` already exists → one line: "There's existing engagement memory here. Continuing this or starting fresh?"
 3. **Access.** If the FDE is about to start work → one line: "Got repo and environment access sorted, or is that still pending?"
 

package/skills/brief/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/build/.fde-generated.json

@@ -11,7 +11,7 @@
     "references/qa.md": "41de4d70827c83291efa217e97d777f62ec2849827687fbba7e4b1d17484b87e",
     "references/review.md": "8fa35eacdc04d5e818e046e6da8f61f126e08d9c6a1073b2eaa19f72d4bfea3a",
     "references/ship.md": "95f51772b29de6f7d174f1f7678f15d46a3a5327dcb8facb94288e27907ae92c",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd",
     "references/verification.md": "8ee2502112a37eedfdacf929041e7b91e9e6fabb007408a1ee2e2992e3af6ff6"
   }
 }

package/skills/build/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/business-case/.fde-generated.json

@@ -5,6 +5,6 @@
     "SKILL.md": "1105f7e78b5e73e54aafb8150e03be8c3ccd3443bc3ae667555763a839c1abe4",
     "agents/openai.yaml": "dd2676346caea1b53ae2bee6662aea064eea74c8ca6edf721382526f5fc42ef5",
     "references/business-case.md": "32e000e8351cd59f9eaad8be40babb276df69948ea4f81e01a4672e47f48cb25",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/business-case/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/connect/.fde-generated.json

@@ -8,6 +8,6 @@
     "references/debrief.md": "2e8e929f1c741e1a7250ad720dfa2196e1f8b14ae84f17e406c38910b9b83376",
     "references/ingest.md": "2aaf948f6ae19fb472a2bf101b8064fc04e3c1103b874455b5a4457b5c69cf86",
     "references/source-setup.md": "a28ae7c6dbb2573a66f31b30b7abca34bc52573fe34d48fff4c7490e4dc85d3e",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/connect/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/dashboard/.fde-generated.json

@@ -5,6 +5,6 @@
     "SKILL.md": "e06df3f2da2586c14e12f2599091231083c0a2f43af70b427c0ab307641610a3",
     "agents/openai.yaml": "abbfc923f66cea302d6fb06b02ff5d2a9f9faa24f30904344785abab1e627999",
     "references/dashboard.md": "dd842c17a2689a6017fecf34a6a24ee5cd40f504af4397eaeb2493ef4ffceda0",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/dashboard/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/debrief/.fde-generated.json

@@ -8,6 +8,6 @@
     "references/debrief.md": "2e8e929f1c741e1a7250ad720dfa2196e1f8b14ae84f17e406c38910b9b83376",
     "references/ingest.md": "2aaf948f6ae19fb472a2bf101b8064fc04e3c1103b874455b5a4457b5c69cf86",
     "references/source-setup.md": "a28ae7c6dbb2573a66f31b30b7abca34bc52573fe34d48fff4c7490e4dc85d3e",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/debrief/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/debug/.fde-generated.json

@@ -11,7 +11,7 @@
     "references/qa.md": "41de4d70827c83291efa217e97d777f62ec2849827687fbba7e4b1d17484b87e",
     "references/review.md": "8fa35eacdc04d5e818e046e6da8f61f126e08d9c6a1073b2eaa19f72d4bfea3a",
     "references/ship.md": "95f51772b29de6f7d174f1f7678f15d46a3a5327dcb8facb94288e27907ae92c",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd",
     "references/verification.md": "8ee2502112a37eedfdacf929041e7b91e9e6fabb007408a1ee2e2992e3af6ff6"
   }
 }

package/skills/debug/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/demo-prep/.fde-generated.json

@@ -5,6 +5,6 @@
     "SKILL.md": "a9c477a1f2f2d44ba1893ea1299c3b30f07c772064b8c28d5bb31d87f032ef67",
     "agents/openai.yaml": "14df03f4ac1652773b277fbe8e9c501f253dbe550b29f4df1ec0e15a9b6eb6aa",
     "references/demo-prep.md": "2166d4104c8da995ea1dbdf27e36fe288a83c6e18ff1de2650fb0eec769ec84f",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/demo-prep/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/discover/.fde-generated.json

@@ -6,6 +6,6 @@
     "agents/openai.yaml": "77306e5aa72884b8c06afe91ae4991910bf3ad38a72375c2fc5251fc7744789a",
     "references/audit.md": "ed32ea78cbccb100742dd838e8cf4cd4b6f33ad44b3de7424fc624670d571dbc",
     "references/discover.md": "f65aa11a539b4dbbed70cfaa94ec2a35595aa9a2d0282790510b933ac9c721ce",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/discover/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/earn-trust/.fde-generated.json

@@ -5,6 +5,6 @@
     "SKILL.md": "a739454cd58e6beba57877e8b1c0d888d1068617b63959014c7b142fd12d68c3",
     "agents/openai.yaml": "3157721445a01f3f840106c23f775305155946669cf44d056e5eb4641f47a84d",
     "references/earn-trust.md": "ec31c339a39d9a7f3855ff77478684bc1d6cae473362489456f0c17b64c33399",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/earn-trust/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/evaluate/.fde-generated.json

@@ -11,7 +11,7 @@
     "references/qa.md": "41de4d70827c83291efa217e97d777f62ec2849827687fbba7e4b1d17484b87e",
     "references/review.md": "8fa35eacdc04d5e818e046e6da8f61f126e08d9c6a1073b2eaa19f72d4bfea3a",
     "references/ship.md": "95f51772b29de6f7d174f1f7678f15d46a3a5327dcb8facb94288e27907ae92c",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd",
     "references/verification.md": "8ee2502112a37eedfdacf929041e7b91e9e6fabb007408a1ee2e2992e3af6ff6"
   }
 }

package/skills/evaluate/references/task-context.md

@@ -3,6 +3,7 @@
 Use this contract for standalone methods and methods routed through `@fde`.
 
 - **Standalone work:** use the supplied, permitted facts, notes, code, and artifacts. A client name, `.fde/` directory, or initialized engagement is not a prerequisite for work on supplied context. Tasks that inspect actual records need those records; staging or saving requires a selected customer. Never fabricate records to make an operational task appear complete. Do not bootstrap records merely to run a method. Ask only for missing information or authority that changes the next action; mark other gaps as unknown.
+- **Fit the method to the engagement:** choose the smallest useful next action from the outcome, uncertainty, dependencies, consequence of failure, available access and time. Duration alone does not choose the process: a three-day production change may need more controls than a three-week prototype. Reuse the customer's tools, review cadence and approved evidence; load specialist methods only for a relevant decision or failure. For a simulation, use the supplied actors and constraints without inventing meetings or authority. Expand coordination when dependencies or risk require it, and simplify again when they are resolved. A deadline can reduce scope or change the proposed delivery stage; it cannot silently waive acceptance, data policy or release authority. Judge progress by the requested result and evidence, whether that is a working increment, a resolved decision or a validated finding; record volume is not progress.
 - **Artifact names are destinations:** names such as `success.md`, `decisions.md`, and `delivery.md` identify relevant evidence and, when bound, record destinations. If absent, use supplied facts and return the requested draft or result in the current workspace or conversation. Do not invent files or require initialization to complete useful work.
 - **Bound engagement:** honor the current client binding and constraints. Before reading records, run `fde privacy` to verify masking support. Obtain a fresh, identity-matching sanitized `fde resume` packet for this task (or reuse a fresh session-hook packet); retrieve missing evidence with targeted `fde recall <topic>`. Use bounded `fde handoff` for transfer work. Refresh after binding, masking, or record changes. Never substitute raw `.fde/` reads, private blocks, masking dictionaries, or full transcripts. If the CLI is unavailable, use only permitted supplied excerpts and report the context limitation.
 - **Authority:** continue reversible work within authorized scope. Reuse prior authorization when it covers the specific action. Show consequential engagement-record judgments and uncertainties for confirmation before saving unless already explicitly confirmed. New scope, acceptance changes, production actions, exports, and external messages need the applicable authority; a method invocation alone does not supply it. Keep one customer's writes in that customer's record.

package/skills/fde/SKILL.md

@@ -164,7 +164,7 @@ Work names (engage, diagnose, align, deliver, realize, transfer) are the same ma
 | Payments, cardholder data, PCI-DSS, anything that moves money | `references/fintech.md` |
 | Government agency, FedRAMP, ATO, CUI, classified | `references/gov.md` |
 
-Ready to build: check that the supplied facts establish the outcome, constraints and verification path. Use discover or plan only for material gaps. On a takeover, audit inherited claims that affect the task. Two customers in one message: confirm which folder.
+Ready to build at any point in an engagement: check that the supplied facts establish the outcome, constraints and verification path, then use `build` for the working slice. Use discover or plan only for a material gap or a real sequencing decision; do not run every stage or create records to demonstrate activity. On a takeover, audit inherited claims that affect the task. Two customers in one message: confirm which folder.
 
 ## Principles
 

package/skills/fde/references/ai.md

@@ -2,7 +2,7 @@
 
 **Activate when you hear:** AI, ML, machine learning, model, LLM, GPT, inference, embeddings, RAG, agents, fine-tuning, prompt engineering, training data, model drift, hallucination, vector database, neural network, generative AI. Loads **alongside** the active phase, never instead of it.
 
-**Read first:** `trust-profile.md` always - AI policy and data classification before any action. `terrain.md` when reviewing existing AI components.
+**Read first:** apply [task context](task-context.md). Use permitted AI-policy and data-classification evidence from the supplied brief or existing `trust-profile.md`; use `terrain.md` when reviewing existing AI components. Missing records do not block standalone work.
 
 AI systems fail differently from traditional software: they **degrade silently** instead of throwing exceptions. A model that hallucinates returns a 200 OK with confident nonsense. A drifted model passes every unit test while making worse decisions. The monitoring, testing, and governance patterns for AI are fundamentally different.
 
@@ -10,13 +10,13 @@ AI systems fail differently from traditional software: they **degrade silently**
 
 > "Is there an existing AI/ML policy? Who approves production use of AI? What data can leave the network?"
 
-Get these answers before any AI code is written:
+Resolve the following before the action that depends on them: customer-data use, a paid model call or production release. Reuse supplied answers. While approval is pending, an authorized local prototype can use synthetic inputs and stubbed model responses; label what that does not verify.
 - **Model hosting:** cloud API (OpenAI, Anthropic, Google) or self-hosted? Cloud = data leaves the network. Self-hosted = infra cost and maintenance.
 - **Data classification:** what data touches the model? PII in prompts = a compliance conversation before a technical one.
 - **Human-in-the-loop requirements:** which decisions require human review before action? In regulated industries, autonomous AI decisions may be prohibited.
 - **Budget/cost model:** AI inference costs scale with usage. What's the expected volume? What's the cost ceiling?
 
-Record in `trust-profile.md` under `## AI policy`.
+For a bound engagement, record confirmed policy in `trust-profile.md` under `## AI policy`; otherwise retain the supplied constraints with the task.
 
 ## Model selection - choosing the right tool
 
@@ -38,7 +38,7 @@ Write model selection rationale to `decisions.md`. Include: models tested, test
 
 ## Engagement eval pack (before AI ships)
 
-When any slice touches a model, embeddings, RAG, or an agent: create or update `.fde/evals.md` **before** ship. Full skill: `references/eval-pack.md`. This is the engagement-local test set - not unit tests.
+Before releasing model, embedding, RAG or agent behavior, use [eval-pack](eval-pack.md) with evidence proportional to the intended use and risk. Reuse the project’s existing evaluation artifact; in a bound engagement, link or update `.fde/evals.md`. Standalone work does not require a customer record. A synthetic demo result does not establish production readiness.
 
 **Minimum pack (do not grow until the minimum exists):**
 1. **Component + quality bar** - one sentence each; kill switch / fallback named.

package/skills/fde/references/fintech.md

@@ -2,7 +2,7 @@
 
 **Activate when you hear:** payments, transfers, settlements, reconciliation · PCI-DSS, PSD2, SOX, open banking, SWIFT · banking, lending, insurance, trading, crypto · "we handle money" in any form. Loads **alongside** the active phase, never instead of it.
 
-**Read first:** `trust-profile.md` always - data classification and AI policy before any action. `terrain.md` only when reviewing transaction/cardholder code.
+**Read first:** apply [task context](task-context.md). Use permitted data-classification and AI-policy evidence from the supplied brief or existing `trust-profile.md`; use `terrain.md` when reviewing transaction/cardholder code. Resolve missing permissions before the affected action; continue independent analysis using permitted evidence.
 
 Financial systems carry a failure class others don't: **silent money loss.** A bug that processes a payment twice or drops a transaction is regulatory breach + customer harm + potential criminal liability, not a defect ticket.
 

package/skills/fde/references/land.md

@@ -4,6 +4,8 @@
 
 **Read first:** apply [task context](task-context.md), then permitted `context.md` evidence if it exists and the supplied brief. Once the engagement type and AI/access policy are known, inspect the supplied repo/docs relevant to the ask before asking questions they can answer. This is a bounded evidence check, not a full discovery scan.
 
+**Bounded engagement:** A new customer does not automatically require a full landing exercise. For a single-outcome task or simulation of any duration, use the supplied brief to establish the outcome, deadline, permitted inputs, acceptance and next authorized action. If those are clear, route to the working task immediately. If one material gap remains, investigate that gap; do not build a stakeholder map or populate engagement files for their own sake. A simulated stakeholder does not justify invented meetings or approval chains. Keep actual data and release authority checks where they affect the work.
+
 ## Validation gate (confirm understanding, clarify where it elevates)
 
 Before landing, state what you know in 2-3 lines:
@@ -12,7 +14,7 @@ Before landing, state what you know in 2-3 lines:
 
 Then check - probe ONLY if it prevents a bad start:
 
-1. **Engagement speed.** If timeline is unclear → weave it in naturally: "Is this days, weeks, or months? That shapes how much structure we set up now."
+1. **Deadline and scope.** Ask about timing only when it changes the next action: "What result is needed by when?" Use uncertainty, dependencies, risk and access to choose the necessary structure; duration alone does not decide it.
 2. **Existing context.** If `.fde/` already exists → one line: "There's existing engagement memory here. Continuing this or starting fresh?"
 3. **Access.** If the FDE is about to start work → one line: "Got repo and environment access sorted, or is that still pending?"
 

package/skills/fde/references/pick-three.md

@@ -29,23 +29,23 @@ Notice: every stakeholder's initiative is P0 or P1. That's the problem this skil
 | **Dependency** | How many other initiatives are blocked waiting for this? | 0 (standalone) → 5 (critical path for 3+ others) |
 | **Cost of delay** | What happens each week this doesn't ship? | 1 (nothing) → 5 (measurable loss or regulatory exposure) |
 
-**Triage score = Impact + Dependency + Cost of delay** (simple sum, 3-15 range).
+**Triage score = Impact + Dependency + Cost of delay** (simple sum, 2-15 range).
 
 **3. Sort into three lanes:**
 
 | Lane | Score | Action |
 |------|-------|--------|
-| **Now** (max 3) | 11-15 | Active work this phase. FDE and team capacity allocated. |
-| **Next** (max 5) | 7-10 | Sequenced for the following phase. Dependencies tracked but not started. |
-| **Later** (unlimited) | 3-6 | Captured, not committed. Revisit at next triage. |
+| **Now** (max 3) | 11-15 | Proposed active work, subject to actual capacity, dependencies and authority. |
+| **Next** (max 5) | 7-10 | Proposed sequencing; dependencies tracked but not started. |
+| **Later** (unlimited) | 2-6 | Captured, not committed. Revisit at next triage. |
 
-**The cap matters.** "Now" has exactly 3 slots. Not 4, not "3 plus this small one." Discipline is the product.
+**The cap matters.** Three is a maximum, not a quota. Use fewer or zero Now items when capacity, unresolved dependencies or required permissions prevent useful authorized work. Check who is available, effort within the phase and shared bottlenecks; one engineer cannot be allocated to several full-capacity initiatives at once. The score bands are a starting point, not automatic lane assignments: high-scoring blocked work waits, and a lower-scoring prerequisite may come first with an explained rationale. Keep uncertain allocations proposed rather than inventing capacity or approval.
 
 **4. Handle the political override.** When a powerful stakeholder pushes a low-scoring initiative into "Now":
 
-- Show the displacement: "Adding X to Now means Y drops to Next. Y is currently blocking Z and W."
-- Let them choose: "Which of the current three should Y replace?" Making the trade-off visible makes the conversation honest.
-- If they override without trading: log it. `decisions.md`: "Initiative X added to Now without displacement by <who>. Capacity impact: <what slows>."
+- Show the capacity and dependency trade-off. If Now is full for the available team, adding X requires deferring work or an explicitly agreed capacity change; a vacant slot alone is not capacity.
+- Ask the responsible decision-maker to resolve the actual choice, without assuming three items are already active. Record the supplied choice and its source under the existing confirmation rules.
+- An override cannot waive required permissions or create capacity. Keep an unresolved request proposed, with its impact, rather than reporting it as an allocated commitment.
 
 **5. Set the triage cadence.** Triage is not a one-time event:
 
@@ -55,15 +55,15 @@ Notice: every stakeholder's initiative is P0 or P1. That's the problem this skil
 | Standard (1-4 weeks) | Weekly | New P0 from sponsor |
 | Programme (months) | Bi-weekly | Quarterly review, team change, market shift |
 
-**6. Communicate the triage result.** The output is not just a priority list - it's a commitment:
+**6. Communicate the triage result.** Distinguish a proposed allocation from an authorized commitment:
 
-> "We're committing to these three initiatives this phase: [A, B, C]. Here's why, here's what they deliver, and here's what's explicitly deferred: [D, E, F, ...]. If priorities change, we re-triage - we don't add without removing."
+> "For the available capacity, I propose [eligible items, or none] this phase. Here's what they deliver, what is blocked or deferred, and which allocation still needs confirmation. Existing agreed work remains agreed; changes need the appropriate decision authority."
 
 ## Artifact
 
-**`decisions.md`** - the triage table with scores, lanes, **and an explicit Kill / Later commitment**. Dated. Updates the same Now/Next/Later plan already uses; do not open a second plan section. Referenced by plan and status.
+**`decisions.md`** - the triage table with scores, lanes, and proposed or agreed deferrals. Keep status and decision sources explicit. Update the same Now/Next/Later section plan already uses under the record-confirmation rules; do not open a second plan section. Standalone work returns the draft without initializing records.
 
-Required closing block (plan will not treat triage as done without it):
+For a recorded triage result, preserve this closing block. A draft may contain pending allocations and deferrals; missing agreement must not be filled with invented acceptance:
 
 ```markdown
 ## Triage - <date>
@@ -75,21 +75,21 @@ Required closing block (plan will not treat triage as done without it):
 ### Kill / defer (not this phase)
 | Initiative | Why not now | Who accepted |
 |------------|-------------|--------------|
-| ... | ... | <name, date> |
+| ... | ... | <pending, or supplied name, date and source> |
 
-Commitment: we ship only Now. Additions require a removal.
+Allocation: <proposed, or agreed with source>. Now contains only work feasible within the stated capacity and authority. Additions require a capacity and dependency check, and displacement when full.
 ```
 
 **`reality.md`** - if triage revealed that the engagement scope is larger than the timeline supports, update the assessment.
 
 ## Checkpoint
 
-Walk the FDE through: the 3 "Now" initiatives and why, the top "Next" items and what triggers their promotion, and the one initiative that will generate the most political pushback for being in "Later." Prepare the FDE for that conversation.
+Walk the FDE through: the proposed or agreed Now items and available capacity, the Next items and what enables their promotion, and any real trade-off requiring a decision. Explain an empty Now lane when applicable; do not fill it to satisfy the title.
 
 ## Principles
 
-- "Now" has 3 slots. Not 4. Discipline is the product.
-- Every addition requires a removal. Visible trade-offs beat invisible overload.
+- Now has at most three items and must fit actual capacity and dependencies.
+- Every addition requires a capacity check; displace work when full rather than silently overloading the team.
 - Triage is recurring, not one-time. The list changes; the discipline doesn't.
 - A logged override protects the FDE. An unlogged override blames them.
 - The initiative everyone wants but nobody will trade for is the one to watch.