fdeops 5.1.22 → 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/mcp/fdeops-ingest/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fdeops-ingest-mcp",
-  "version": "5.1.22",
+  "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": "5.1.22",
+  "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": "5.1.22",
+  "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/plan.md

@@ -4,7 +4,9 @@
 
 **Enter when:** scope is understood and the work needs breaking down - a slice, a phase, or the whole delivery.
 
-**Read first:** `reality.md`, `success.md`, `terrain.md`, `stakeholders.md`. Load `business-case.md` if poc produced one. Not the full folder.
+**Read first, when an engagement record exists:** the relevant parts of `reality.md`, `success.md`, `terrain.md`, and `stakeholders.md`. Load `business-case.md` only when its cost case affects this decision. For standalone work, use the supplied context; absent records are not a blocker.
+
+**Bounded path:** If implementation is requested and authorized, and the outcome, constraints and acceptance checks already support one bounded change, the coordinator can select `build` without a separate planning exercise. An explicit planning request still returns a plan; it does not authorize implementation or require another installed skill. If a bounded task genuinely needs sequencing, give the FDE a brief plan with the next working slice, its boundary, a success and failure check, and the blocking unknown or authority if any. Spend the time on the working result. A single-slice plan does not require a new engagement record, stakeholder map or multi-phase template.
 
 **On an initialized engagement, before a new delivery plan or material scope change:** run `fde doctor --ready`. For standalone planning, check the supplied outcome, scope, acceptance and authority directly; do not initialize records to run this validator. Missing acceptance criteria or authority blocks the affected implementation commitment, not a provisional plan. Draft proposed checks and next steps, mark them pending, and ask only what changes the next action. Use a test/input and observable pass/fail under **Done when:** or **Acceptance check:**. A number, role, or successful demo alone is insufficient. Do not invent missing facts to pass lint. Routine reversible fixes within confirmed scope reuse the existing signer, acceptance criteria, and engineering plan; record verification without reopening settled decisions.
 
@@ -46,7 +48,7 @@ Preserve supplied ticket identifiers and blocking dependencies; do not renumber
 
 **6. Agree useful stakeholder touchpoints.** Name who needs to see which result before the next decision. Reuse the customer's existing review cadence; task count alone does not justify another meeting or imply lost trust.
 
-**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. Keep **Now** small enough to review and act on; split by independently verifiable outcomes.
+**7. Bound a multi-slice plan.** For a phased engagement, name consequential work excluded from this phase. Do not invent a kill list for one bounded slice. Keep **Now** small enough to review and act on; split by independently verifiable outcomes.
 
 Carry the agreed acceptance checks and their source into implementation and verification, preferably by linking the existing record. Added checks may strengthen coverage; changing a threshold or removing a requirement remains a proposal until the appropriate decision-maker approves the change with a dated source. Record what changed and why; a passing weaker test does not satisfy the original agreement.
 
@@ -56,7 +58,7 @@ Carry the agreed acceptance checks and their source into implementation and veri
 
 For standalone planning, return the requested draft or save to the authorized project document. In a bound engagement, propose the plan for **`decisions.md`** under its confirmation rules, or link the existing approved plan; do not duplicate it.
 
-A plan is **not done** until all four blocks exist:
+For a single-slice plan, the brief slice, boundary, acceptance checks, verification and any blocking dependency are enough. Use the full four-block format below when sequencing several slices or decisions with material dependencies, regardless of engagement duration:
 
 ```markdown
 ## Plan - <date>
@@ -92,7 +94,7 @@ In `Who accepted`, distinguish a proposed deferral from an agreement: use `pendi
 Check the plan against every supplied requirement and constraint. Each must map to a task and acceptance check, an explicitly accepted exclusion, or a visible unresolved decision. Do not silently omit a requirement to simplify the plan. Reuse an existing approved plan rather than creating a second coverage record. If no work is deferred, say so; do not invent exclusions to fill the template.
 ## Checkpoint
 
-Walk the FDE through: sequence + why this order, where the fragile work sits, where the touchpoints land, the acceptance gate and **Kill if** on task 1, and the kill list. State who sees the first slice and when, which exclusions are accepted or proposed, and what observation stops task 1. Reuse supplied answers; ask only about a missing or consequentially ambiguous answer.
+For a single-slice plan, state the first slice, how it will be checked, and what would stop it. For a phased plan, walk the FDE through the sequence, fragile work, useful touchpoints, acceptance gate, and consequential exclusions. Reuse supplied answers; ask only about a missing or consequentially ambiguous answer.
 
 ## Method - estimation (when the sponsor asks "how long, how much?")
 
@@ -157,7 +159,7 @@ First visible slice goes to Marco, not Priya: he is the one whose morning change
 - Fragile zones early. Fail fast.
 - Touchpoints serve the next customer decision and agreed cadence.
 - No written acceptance criteria, no build.
-- No kill list, no finished plan.
+- Make consequential exclusions explicit when work is deferred; a bounded slice needs no invented kill list.
 - No **Kill if** on a Now PR, that PR is hope.
 - Estimates are ranges, not promises. Name the assumptions and the observation that voids them.
 - Migrations: compatibility determines order; verified recovery precedes cutover.

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

@@ -5,6 +5,6 @@
     "SKILL.md": "7d49a9e89736e35c2aaf10c78b10be365bdf91af1aaf99430de6069e96069d55",
     "agents/openai.yaml": "6b8d024e9ea9676a2607b76a6f1fcd2fbcba585af2990b1172dbdb8cec0364c6",
     "references/encode-pattern.md": "10fc5679752f0ea0b4d3004e4c7e282bb17f9b496ab99e5c7aae04ac942fb3c1",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/feedback/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/handoff/.fde-generated.json

@@ -6,7 +6,7 @@
     "agents/openai.yaml": "93ac049cf1a9d0fdfdf67d34ca6d3dd33800e91334f38bb303828eab8c4b3aaf",
     "references/close.md": "4c75697bb7c85af3b4054bf427d0f265d388972a3139f1e25a1bc9f56ac65cf4",
     "references/encode-pattern.md": "10fc5679752f0ea0b4d3004e4c7e282bb17f9b496ab99e5c7aae04ac942fb3c1",
-    "references/land.md": "87dfffc8e39d35eaf23d510ba7e9913d48e90d2705eb9155ab192d12ea98d18d",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/land.md": "f33f1b9e03a3c23c39ffce925a8f8b956b48a53982f55246752a48a317cb084d",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/handoff/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?"