fdeops 5.1.21 → 5.1.23

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

@@ -7,6 +7,6 @@
     "references/board-memo.md": "44eb3c27f164da63af694591025b3fc96bb23d149c29de400997c1653e3322f8",
     "references/business-case.md": "32e000e8351cd59f9eaad8be40babb276df69948ea4f81e01a4672e47f48cb25",
     "references/readout.md": "485301ef5e6e333f0272aec0b6428839077341b228506c6e77f79cce22399903",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/readout/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/red-team/.fde-generated.json

@@ -5,6 +5,6 @@
     "SKILL.md": "e406016f3cf7b715084bde0081bec03706a695e6272ada2e51ff3cb9d5194de5",
     "agents/openai.yaml": "c6cac62d94f5294f981de12539dca0a8aa601cea3357fedd94083f4fd1cb0d48",
     "references/red-team.md": "31aaa96f2bac337daa8fc8abf1ddbef745d7ab7a8b77776d2fbb2dd59f4782ce",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/red-team/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/rescue/.fde-generated.json

@@ -5,6 +5,6 @@
     "SKILL.md": "de58cdfb46219c71c85b4e940bffe0e52d8511f4dede803d0efe1bf46aa5ac5c",
     "agents/openai.yaml": "d88d5433332c8269c8342589bc88ef9df7b0f7b0224e4b8ee5a00bc5d96f5e2e",
     "references/rescue.md": "3af07633b82dc1022bafc86173f6c55da81501317e25c9ac8980cfcb04b27df3",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/rescue/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/review/.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/review/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/rollback/.fde-generated.json

@@ -5,6 +5,6 @@
     "SKILL.md": "19645edc8853a4b1ca7f3dacbf48ed553d7f630939c81c9254c00808fdebedc8",
     "agents/openai.yaml": "d8fa5d46f05dd1501993f40b0c8e205f061c5b4de754046d9059cb0c3d8c88f9",
     "references/rollback.md": "cdde85caeb8e556825d0c3a156cd16d6e41550931984429e4978486ee91854cd",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/rollback/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/runbook/.fde-generated.json

@@ -6,9 +6,9 @@
     "agents/openai.yaml": "53922bbe55ba23dc812c9bef311fbef238e2e25252100bdac7a8bd4f6c5e2780",
     "references/close.md": "4c75697bb7c85af3b4054bf427d0f265d388972a3139f1e25a1bc9f56ac65cf4",
     "references/encode-pattern.md": "10fc5679752f0ea0b4d3004e4c7e282bb17f9b496ab99e5c7aae04ac942fb3c1",
-    "references/land.md": "87dfffc8e39d35eaf23d510ba7e9913d48e90d2705eb9155ab192d12ea98d18d",
+    "references/land.md": "f33f1b9e03a3c23c39ffce925a8f8b956b48a53982f55246752a48a317cb084d",
     "references/runbook.md": "d32a40113941c603b97f09eabfd0e25afd25129102c6b07fa91a04fb4f8e93e7",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd",
     "references/verification.md": "8ee2502112a37eedfdacf929041e7b91e9e6fabb007408a1ee2e2992e3af6ff6"
   }
 }

package/skills/runbook/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/runbook/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/scope/.fde-generated.json

@@ -5,6 +5,6 @@
     "SKILL.md": "544424180d2e924e21e98e94c1d6a35c067176ff9876f6c11415638e041f89f5",
     "agents/openai.yaml": "22b669e628e4401c6b042d17fca25f0259593d90a581e232816c140e788306ec",
     "references/hold-scope.md": "651ba25570401ceda8dc518d1037f1644ee09a0166609b93d437164e4dc45837",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/scope/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/score-use-cases/.fde-generated.json

@@ -5,7 +5,7 @@
     "SKILL.md": "d3abc46b68361f6d808191b50183d41eec65eac31cba5d53ef1e22a2ccd7b32f",
     "agents/openai.yaml": "8f4af12758edb1a4648bb7917ef4c52eb4eb209a3917ae3e04904cdd5fd4dec0",
     "references/business-case.md": "32e000e8351cd59f9eaad8be40babb276df69948ea4f81e01a4672e47f48cb25",
-    "references/score-use-cases.md": "bb304cf2de26a2df0b9f2a299e3a6b2760ebce15b8b523d9cb4a584cc26038f8",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e"
+    "references/score-use-cases.md": "a8352b0886731a647fdb0305b22eaa83244f367d797e130ceb3271f112886801",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd"
   }
 }

package/skills/score-use-cases/references/score-use-cases.md

@@ -4,13 +4,15 @@
 
 **Read first:** `reality.md`, `brief.md`, `terrain.md`, `context.md`. If `business-case.md` or `prototype-log.md` exist from poc, load those - they carry forward.
 
-The most dangerous moment in a multi-use-case engagement is when the technically interesting problem wins over the high-value problem. Scoring replaces opinion with arithmetic. The arithmetic is wrong - all models are - but it's *visibly* wrong, which means it can be debated and corrected. Opinion can't.
+The most dangerous moment in a multi-use-case engagement is when the technically interesting problem wins over the high-value problem. Scoring makes assumptions and trade-offs visible; it does not replace evidence or judgment. These ordinal ratings are a discussion aid, not calibrated estimates of value or a reason to override a hard constraint.
 
 ## Method (you do this work)
 
 **1. List every candidate.** From the brief, from discovery conversations, from the FDE's own observations. Include the ones the customer hasn't said aloud but the codebase implies - a high-churn module with no tests is a candidate even if nobody named it.
 
-**2. Score on five dimensions.** Each 1-5, with the scoring rubric below. If discover already ranked candidates with (Value × Data readiness) / Complexity, reuse that order; this table extends the conversation. Do not invent dimension scores from a thin brief - write `unknown` and ask.
+Before ranking work for the proposed step, identify hard feasibility, access, data-permission and policy constraints. Keep blocked or unverified candidates visible with the affected step, owner or authority gap, and evidence needed to reconsider. A high score cannot make dependent work eligible. An authorized design or evidence check may proceed while implementation is blocked; a sponsor's preference does not grant missing API or data permission.
+
+**2. Score on five dimensions.** Each 1-5, with the scoring rubric below. Reuse discovery's evidence and rationale, rechecking whether the candidates are eligible for the same next step. Do not invent dimension scores from a thin brief - write `unknown`, return a conditional recommendation and ask only what changes the decision.
 
 | Dimension | 1 | 3 | 5 |
 |-----------|---|---|---|
@@ -27,11 +29,11 @@ Score = (Business value × Urgency × Stakeholder alignment) / (6 - Feasibility)
 ```
 
 Why this formula:
-- **Multiplied numerator** - all three must be present. A high-value problem with no urgency or no sponsor scores low because it won't ship.
+- **Multiplied numerator** - a lower rating reduces the score relative to otherwise identical ratings. Because every scale starts at 1, the formula does not establish that urgency, sponsorship or permission is present; eligibility must be checked separately.
 - **Feasibility inverted** - harder problems get a higher denominator, pulling the score down. A feasibility of 5 (easy) gives denominator 1; feasibility of 1 (hard) gives denominator 5.
 - **Data readiness as multiplier** - for data-dependent use cases (ML, analytics). For pure engineering work, set to 3 (neutral) unless data quality is genuinely a factor.
 
-**4. Rank and present.** Sort by score. Present the top 3 to the FDE and the sponsor:
+**4. Rank and present.** Compare eligible candidates; show up to three useful options and list blocked work separately. If an uncertain input could reverse the order, show the plausible alternative rankings and the smallest permitted check that distinguishes them, with its owner or an explicit ownership gap. Do not hide uncertainty in a precise-looking score or delay independent authorized work while waiting. The following scores illustrate a recommendation, not a commitment:
 
 ```markdown
 | Rank | Use case | Value | Urgency | Feasibility | Data | Alignment | Score | Recommend |
@@ -49,7 +51,7 @@ Why this formula:
 **6. Handle the CEO's pet project.** Sometimes the highest-scoring use case isn't the one the most powerful stakeholder wants. That's information, not a problem:
 
 - Present the scores honestly - the stakeholder sees you're being rigorous, not political.
-- If they override: log it in `decisions.md` as a deliberate choice, note the trade-off, and build what they chose. The FDE who was honest about the trade-off is protected when the override creates problems.
+- If the responsible decision-maker overrides the ranking, preserve the choice, source and trade-off under the existing record-confirmation rules. Check capacity and required permissions before dependent work; an override changes preference, not hard constraints or acceptance authority. An unconfirmed choice remains proposed.
 
 ## Artifact
 
@@ -59,12 +61,12 @@ Why this formula:
 
 ## Checkpoint
 
-Walk the FDE through the top 3 scores and the recommendation. One question: "Does the sponsor have a strong preference that overrides the scoring?" If yes, log it. If no, proceed with the highest score to poc or plan.
+Walk the FDE through the eligible options, relevant blockers and any uncertainty that could reverse the recommendation. Keep the proposed allocation pending the appropriate decision authority; silence is not approval. Reuse existing authorization when it covers the next step. If evidence is insufficient, recommend a bounded distinguishing check rather than automatically proceeding with the highest score.
 
 ## Principles
 
-- Score replaces opinion. Visible arithmetic beats invisible judgment.
-- All three conditions (value, urgency, alignment) must hold - or the use case won't ship.
+- Scores expose assumptions; evidence and eligible scope govern the recommendation.
+- A numerical advantage cannot override a hard constraint or unknown permission.
 - The technically interesting problem that scores low gets deferred, not pursued.
 - Present the model; let the human decide. If overridden, log the trade-off.
 - A use case with no active sponsor is a research project, not an engagement deliverable.

package/skills/score-use-cases/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/ship/.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/ship/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/switch-clients/.fde-generated.json

@@ -5,7 +5,7 @@
     "SKILL.md": "ebfebe6e5872800c749659aec45af48b2287db2e72c0b914118482e4c73334b5",
     "agents/openai.yaml": "67ecd37a1e5bd57986d800a782aeff8d00171d6d09794b6026d8daf1e2d91e6f",
     "references/switch-clients.md": "4c13df4441182f6ef9455e0abed4facdb6d1c99dd5d10de278708f0bc07f631f",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd",
     "references/verification.md": "8ee2502112a37eedfdacf929041e7b91e9e6fabb007408a1ee2e2992e3af6ff6"
   }
 }

package/skills/switch-clients/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/test-assumptions/.fde-generated.json

@@ -4,7 +4,7 @@
   "files": {
     "SKILL.md": "acba10ec77763f1840c3cda95b26e13150683f6a7557a84a93611f2d96cdd389",
     "agents/openai.yaml": "c67e0342caba79241b1872cdfda8341f4949c2bd7672b8d288b529d8e94342b8",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd",
     "references/test-assumptions.md": "977acbf88dc0468afeb0fb222fae88100ee6a5078a729e0651c28a45870e3925"
   }
 }

package/skills/test-assumptions/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/what-breaks/.fde-generated.json

@@ -4,7 +4,7 @@
   "files": {
     "SKILL.md": "cacffe6b01d36cde634be5e7f8a2127d701d3dac90b3000c414a648956839c5e",
     "agents/openai.yaml": "6c4b97d3268698d1eed0b628f9872351f29b91dd47c9de371a12c584983cb0fe",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd",
     "references/what-breaks.md": "fbf85539fe9c762d713c5772dbef731e96783d369610ba61b66fc220d9e50abf"
   }
 }

package/skills/what-breaks/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/who-decides/.fde-generated.json

@@ -4,7 +4,7 @@
   "files": {
     "SKILL.md": "f5c97755bdeb42cd18dbc1fc79f1d311521efe99fb599d4ebd72b21b6d1dee74",
     "agents/openai.yaml": "fee09f0f2cc7d0c07a1aefa592e10f046abb8951f157ca3336a6233edd3a61ea",
-    "references/task-context.md": "9f995c1fe4d8a27d313b4c008a943fbcdd150029358c70b450dbbfb303a2666e",
+    "references/task-context.md": "3d59235f6b7092c41116457cc54e3e2e67fc0fba7b46b60279bd304be18b10cd",
     "references/who-decides.md": "fa1f65d921943e76f42284570004a603488905417d96b4bd52dc6c4a11dd5a97"
   }
 }

package/skills/who-decides/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.