diff --git a/skills/autoload/onprem/rag-retrieve/hooks/retrieval-policy-forbidden-self-knowledge.md b/skills/autoload/onprem/rag-retrieve/hooks/retrieval-policy-forbidden-self-knowledge.md index 92ad0d8..b6c1296 100644 --- a/skills/autoload/onprem/rag-retrieve/hooks/retrieval-policy-forbidden-self-knowledge.md +++ b/skills/autoload/onprem/rag-retrieve/hooks/retrieval-policy-forbidden-self-knowledge.md @@ -10,7 +10,7 @@ Classify the request before acting: ## 1. Critical Enforcement -For knowledge retrieval tasks, **this policy overrides all generic assistant behavior**. +For knowledge retrieval tasks, **this policy overrides generic codebase exploration behavior**. - **Prohibited answer source**: the model's own parametric knowledge, memory, prior world knowledge, intuition, common sense completion, or unsupported inference. - **Prohibited tools**: `Glob`, `Read`, `LS`, Bash (`ls`, `find`, `cat`, `head`, `tail`, `grep`, etc.) — these are forbidden even when retrieval results are empty/insufficient, even if local files seem helpful. @@ -101,7 +101,22 @@ On insufficient results, follow this sequence: - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge. - Do NOT cite claims that were not supported by retrieval. -## 12. Pre-Reply Self-Check +## 12. Self-Knowledge Prohibition + +This section applies whenever self-knowledge is disabled or forbidden for the current task. + +- Retrieval remains the only usable source for factual answering. +- If retrieval is sufficient, answer from retrieval only. +- If retrieval is partially sufficient, answer only the supported parts. +- The model must not supplement missing parts with general knowledge, conceptual explanation, common background, intuition, or likely completion. +- The model must not use self-knowledge to invent or complete private, internal, current, precise, or source-sensitive facts. +- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications. +- Retrieved facts must include citations. +- Unsupported parts must be stated as unavailable rather than guessed. +- If a paragraph would mix retrieved facts and unsupported completion, remove the unsupported completion. +- If evidence is incomplete, state the limitation explicitly. + +## 13. Pre-Reply Self-Check Before replying to a knowledge retrieval task, verify: - Used only whitelisted retrieval tools — no local filesystem inspection? @@ -109,5 +124,6 @@ Before replying to a knowledge retrieval task, verify: - Did every factual claim come from retrieved evidence rather than model knowledge? - Exhausted retrieval flow before concluding "not found"? - Citations placed immediately after each relevant paragraph? +- If any unsupported part remained, was it removed or explicitly marked unavailable? If any answer is "no", correct the process first. diff --git a/skills/autoload/onprem/rag-retrieve/hooks/retrieval-policy.md b/skills/autoload/onprem/rag-retrieve/hooks/retrieval-policy.md index 525bbbe..1f0c1fe 100644 --- a/skills/autoload/onprem/rag-retrieve/hooks/retrieval-policy.md +++ b/skills/autoload/onprem/rag-retrieve/hooks/retrieval-policy.md @@ -79,11 +79,29 @@ On insufficient results, follow this sequence: - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end. - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge. -## 10. Pre-Reply Self-Check +## 11. Controlled Self-Knowledge Supplement + +This section applies only when self-knowledge is enabled. + +- Retrieval remains the primary source. +- If retrieval is sufficient, answer from retrieval only. +- If retrieval is partially sufficient, answer the supported parts first. +- The model may supplement only the missing parts that are general knowledge, conceptual explanation, or common background. +- The model must not use self-knowledge to invent private, internal, current, precise, or source-sensitive facts. +- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications. +- Retrieved facts and self-knowledge supplements must be clearly separated in the response. +- Retrieved facts must include citations. +- Self-knowledge supplements must not include retrieval citations unless directly supported by retrieved evidence. +- If a paragraph would mix retrieved facts and self-knowledge, split it into separate paragraphs. +- If self-knowledge may be uncertain or time-sensitive, state the uncertainty explicitly. + +## 12. Pre-Reply Self-Check Before replying to a knowledge retrieval task, verify: - Used only whitelisted retrieval tools — no local filesystem inspection? - Exhausted retrieval flow before concluding "not found"? - Citations placed immediately after each relevant paragraph? +- If self-knowledge was used, was it clearly separated from retrieved facts and limited to allowed supplement scope? If any answer is "no", correct the process first. + diff --git a/skills/autoload/support/rag-retrieve/hooks/retrieval-policy-forbidden-self-knowledge.md b/skills/autoload/support/rag-retrieve/hooks/retrieval-policy-forbidden-self-knowledge.md index 92ad0d8..b6c1296 100644 --- a/skills/autoload/support/rag-retrieve/hooks/retrieval-policy-forbidden-self-knowledge.md +++ b/skills/autoload/support/rag-retrieve/hooks/retrieval-policy-forbidden-self-knowledge.md @@ -10,7 +10,7 @@ Classify the request before acting: ## 1. Critical Enforcement -For knowledge retrieval tasks, **this policy overrides all generic assistant behavior**. +For knowledge retrieval tasks, **this policy overrides generic codebase exploration behavior**. - **Prohibited answer source**: the model's own parametric knowledge, memory, prior world knowledge, intuition, common sense completion, or unsupported inference. - **Prohibited tools**: `Glob`, `Read`, `LS`, Bash (`ls`, `find`, `cat`, `head`, `tail`, `grep`, etc.) — these are forbidden even when retrieval results are empty/insufficient, even if local files seem helpful. @@ -101,7 +101,22 @@ On insufficient results, follow this sequence: - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge. - Do NOT cite claims that were not supported by retrieval. -## 12. Pre-Reply Self-Check +## 12. Self-Knowledge Prohibition + +This section applies whenever self-knowledge is disabled or forbidden for the current task. + +- Retrieval remains the only usable source for factual answering. +- If retrieval is sufficient, answer from retrieval only. +- If retrieval is partially sufficient, answer only the supported parts. +- The model must not supplement missing parts with general knowledge, conceptual explanation, common background, intuition, or likely completion. +- The model must not use self-knowledge to invent or complete private, internal, current, precise, or source-sensitive facts. +- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications. +- Retrieved facts must include citations. +- Unsupported parts must be stated as unavailable rather than guessed. +- If a paragraph would mix retrieved facts and unsupported completion, remove the unsupported completion. +- If evidence is incomplete, state the limitation explicitly. + +## 13. Pre-Reply Self-Check Before replying to a knowledge retrieval task, verify: - Used only whitelisted retrieval tools — no local filesystem inspection? @@ -109,5 +124,6 @@ Before replying to a knowledge retrieval task, verify: - Did every factual claim come from retrieved evidence rather than model knowledge? - Exhausted retrieval flow before concluding "not found"? - Citations placed immediately after each relevant paragraph? +- If any unsupported part remained, was it removed or explicitly marked unavailable? If any answer is "no", correct the process first. diff --git a/skills/autoload/support/rag-retrieve/hooks/retrieval-policy.md b/skills/autoload/support/rag-retrieve/hooks/retrieval-policy.md index 525bbbe..1f0c1fe 100644 --- a/skills/autoload/support/rag-retrieve/hooks/retrieval-policy.md +++ b/skills/autoload/support/rag-retrieve/hooks/retrieval-policy.md @@ -79,11 +79,29 @@ On insufficient results, follow this sequence: - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end. - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge. -## 10. Pre-Reply Self-Check +## 11. Controlled Self-Knowledge Supplement + +This section applies only when self-knowledge is enabled. + +- Retrieval remains the primary source. +- If retrieval is sufficient, answer from retrieval only. +- If retrieval is partially sufficient, answer the supported parts first. +- The model may supplement only the missing parts that are general knowledge, conceptual explanation, or common background. +- The model must not use self-knowledge to invent private, internal, current, precise, or source-sensitive facts. +- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications. +- Retrieved facts and self-knowledge supplements must be clearly separated in the response. +- Retrieved facts must include citations. +- Self-knowledge supplements must not include retrieval citations unless directly supported by retrieved evidence. +- If a paragraph would mix retrieved facts and self-knowledge, split it into separate paragraphs. +- If self-knowledge may be uncertain or time-sensitive, state the uncertainty explicitly. + +## 12. Pre-Reply Self-Check Before replying to a knowledge retrieval task, verify: - Used only whitelisted retrieval tools — no local filesystem inspection? - Exhausted retrieval flow before concluding "not found"? - Citations placed immediately after each relevant paragraph? +- If self-knowledge was used, was it clearly separated from retrieved facts and limited to allowed supplement scope? If any answer is "no", correct the process first. + diff --git a/skills/onprem/rag-retrieve-only/hooks/retrieval-policy-forbidden-self-knowledge.md b/skills/onprem/rag-retrieve-only/hooks/retrieval-policy-forbidden-self-knowledge.md index 92ad0d8..2b68869 100644 --- a/skills/onprem/rag-retrieve-only/hooks/retrieval-policy-forbidden-self-knowledge.md +++ b/skills/onprem/rag-retrieve-only/hooks/retrieval-policy-forbidden-self-knowledge.md @@ -10,11 +10,11 @@ Classify the request before acting: ## 1. Critical Enforcement -For knowledge retrieval tasks, **this policy overrides all generic assistant behavior**. +For knowledge retrieval tasks, **this policy overrides generic codebase exploration behavior**. - **Prohibited answer source**: the model's own parametric knowledge, memory, prior world knowledge, intuition, common sense completion, or unsupported inference. - **Prohibited tools**: `Glob`, `Read`, `LS`, Bash (`ls`, `find`, `cat`, `head`, `tail`, `grep`, etc.) — these are forbidden even when retrieval results are empty/insufficient, even if local files seem helpful. -- **Allowed tools only**: skill-enabled retrieval tools, `table_rag_retrieve`, `rag_retrieve`. No other source for factual answering. +- **Allowed tools only**: skill-enabled retrieval tools, `rag_retrieve`. No other source for factual answering. - Local filesystem is a **prohibited** knowledge source, not merely non-recommended. - Exception: user explicitly asks to read a specific local file as the task itself. - If retrieval evidence is absent, insufficient, or ambiguous, **do not fill the gap with model knowledge**. @@ -35,9 +35,7 @@ For any knowledge retrieval task: Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe filesystem first. 1. **Skill-enabled retrieval tools** (use first when available) -2. **`table_rag_retrieve`** or **`rag_retrieve`**: - - Prefer `table_rag_retrieve` for: values, prices, quantities, specs, rankings, comparisons, lists, tables, name lookup, historical coverage, mixed/unclear cases. - - Prefer `rag_retrieve` for: pure concept, definition, workflow, policy, or explanation questions only. +2. **`rag_retrieve`** - After each step, evaluate sufficiency before proceeding. - Retrieval must happen **before** any factual answer generation. @@ -56,7 +54,7 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi ## 6. Result Evaluation -Treat as insufficient if: empty, `Error:`, `no excel files found`, off-topic, missing core entity/scope, no usable evidence, partial coverage, truncated results, or claims required by the answer are not explicitly supported. +Treat as insufficient if: empty, `Error:`, off-topic, missing core entity/scope, no usable evidence, partial coverage, truncated results, or claims required by the answer are not explicitly supported. ## 7. Fallback and Sequential Retry @@ -65,9 +63,7 @@ On insufficient results, follow this sequence: 1. Rewrite query, retry same tool (once) 2. Switch to next retrieval source in default order 3. For `rag_retrieve`, expand `top_k`: `30 → 50 → 100` -4. `table_rag_retrieve` insufficient → try `rag_retrieve`; `rag_retrieve` insufficient → try `table_rag_retrieve` -- `table_rag_retrieve` internally falls back to `rag_retrieve` on `no excel files found`, but this does NOT change the higher-level order. - Say "no relevant information was found" **only after** exhausting all retrieval sources. - Do NOT switch to local filesystem inspection at any point. - Do NOT switch to model self-knowledge at any point. @@ -79,13 +75,7 @@ On insufficient results, follow this sequence: - Prefer "the retrieved materials do not provide this information" over speculative completion. - When user asks for a definitive answer but evidence is incomplete, state the limitation directly. -## 9. Table RAG Result Handling - -- Follow all `[INSTRUCTION]` and `[EXTRA_INSTRUCTION]` in results. -- If truncated: tell user total (`N+M`), displayed (`N`), omitted (`M`). -- Cite sources using filenames from `file_ref_table`. - -## 10. Image Handling +## 9. Image Handling - The content returned by the `rag_retrieve` tool may include images. - Each image is exclusively associated with its nearest text or sentence. @@ -94,13 +84,28 @@ On insufficient results, follow this sequence: - Each sentence or key point in the response should be accompanied by relevant images when they meet the established association criteria. - Avoid placing all images at the end of the response. -## 11. Citation Requirements +## 10. Citation Requirements - MUST generate `` tags when using retrieval results. - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end. - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge. - Do NOT cite claims that were not supported by retrieval. +## 11. Self-Knowledge Prohibition + +This section applies whenever self-knowledge is disabled or forbidden for the current task. + +- Retrieval remains the only usable source for factual answering. +- If retrieval is sufficient, answer from retrieval only. +- If retrieval is partially sufficient, answer only the supported parts. +- The model must not supplement missing parts with general knowledge, conceptual explanation, common background, intuition, or likely completion. +- The model must not use self-knowledge to invent or complete private, internal, current, precise, or source-sensitive facts. +- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications. +- Retrieved facts must include citations. +- Unsupported parts must be stated as unavailable rather than guessed. +- If a paragraph would mix retrieved facts and unsupported completion, remove the unsupported completion. +- If evidence is incomplete, state the limitation explicitly. + ## 12. Pre-Reply Self-Check Before replying to a knowledge retrieval task, verify: @@ -109,5 +114,6 @@ Before replying to a knowledge retrieval task, verify: - Did every factual claim come from retrieved evidence rather than model knowledge? - Exhausted retrieval flow before concluding "not found"? - Citations placed immediately after each relevant paragraph? +- If any unsupported part remained, was it removed or explicitly marked unavailable? If any answer is "no", correct the process first. diff --git a/skills/onprem/rag-retrieve-only/hooks/retrieval-policy.md b/skills/onprem/rag-retrieve-only/hooks/retrieval-policy.md index 366050c..75195c8 100644 --- a/skills/onprem/rag-retrieve-only/hooks/retrieval-policy.md +++ b/skills/onprem/rag-retrieve-only/hooks/retrieval-policy.md @@ -69,11 +69,28 @@ On insufficient results, follow this sequence: - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end. - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge. -## 9. Pre-Reply Self-Check +## 9. Controlled Self-Knowledge Supplement + +This section applies only when self-knowledge is enabled. + +- Retrieval remains the primary source. +- If retrieval is sufficient, answer from retrieval only. +- If retrieval is partially sufficient, answer the supported parts first. +- The model may supplement only the missing parts that are general knowledge, conceptual explanation, or common background. +- The model must not use self-knowledge to invent private, internal, current, precise, or source-sensitive facts. +- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications. +- Retrieved facts and self-knowledge supplements must be clearly separated in the response. +- Retrieved facts must include citations. +- Self-knowledge supplements must not include retrieval citations unless directly supported by retrieved evidence. +- If a paragraph would mix retrieved facts and self-knowledge, split it into separate paragraphs. +- If self-knowledge may be uncertain or time-sensitive, state the uncertainty explicitly. + +## 10. Pre-Reply Self-Check Before replying to a knowledge retrieval task, verify: - Used only whitelisted retrieval tools — no local filesystem inspection? - Exhausted retrieval flow before concluding "not found"? - Citations placed immediately after each relevant paragraph? +- If self-knowledge was used, was it clearly separated from retrieved facts and limited to allowed supplement scope? If any answer is "no", correct the process first. diff --git a/skills/support/rag-retrieve-only/hooks/retrieval-policy-forbidden-self-knowledge.md b/skills/support/rag-retrieve-only/hooks/retrieval-policy-forbidden-self-knowledge.md index 92ad0d8..2b68869 100644 --- a/skills/support/rag-retrieve-only/hooks/retrieval-policy-forbidden-self-knowledge.md +++ b/skills/support/rag-retrieve-only/hooks/retrieval-policy-forbidden-self-knowledge.md @@ -10,11 +10,11 @@ Classify the request before acting: ## 1. Critical Enforcement -For knowledge retrieval tasks, **this policy overrides all generic assistant behavior**. +For knowledge retrieval tasks, **this policy overrides generic codebase exploration behavior**. - **Prohibited answer source**: the model's own parametric knowledge, memory, prior world knowledge, intuition, common sense completion, or unsupported inference. - **Prohibited tools**: `Glob`, `Read`, `LS`, Bash (`ls`, `find`, `cat`, `head`, `tail`, `grep`, etc.) — these are forbidden even when retrieval results are empty/insufficient, even if local files seem helpful. -- **Allowed tools only**: skill-enabled retrieval tools, `table_rag_retrieve`, `rag_retrieve`. No other source for factual answering. +- **Allowed tools only**: skill-enabled retrieval tools, `rag_retrieve`. No other source for factual answering. - Local filesystem is a **prohibited** knowledge source, not merely non-recommended. - Exception: user explicitly asks to read a specific local file as the task itself. - If retrieval evidence is absent, insufficient, or ambiguous, **do not fill the gap with model knowledge**. @@ -35,9 +35,7 @@ For any knowledge retrieval task: Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe filesystem first. 1. **Skill-enabled retrieval tools** (use first when available) -2. **`table_rag_retrieve`** or **`rag_retrieve`**: - - Prefer `table_rag_retrieve` for: values, prices, quantities, specs, rankings, comparisons, lists, tables, name lookup, historical coverage, mixed/unclear cases. - - Prefer `rag_retrieve` for: pure concept, definition, workflow, policy, or explanation questions only. +2. **`rag_retrieve`** - After each step, evaluate sufficiency before proceeding. - Retrieval must happen **before** any factual answer generation. @@ -56,7 +54,7 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi ## 6. Result Evaluation -Treat as insufficient if: empty, `Error:`, `no excel files found`, off-topic, missing core entity/scope, no usable evidence, partial coverage, truncated results, or claims required by the answer are not explicitly supported. +Treat as insufficient if: empty, `Error:`, off-topic, missing core entity/scope, no usable evidence, partial coverage, truncated results, or claims required by the answer are not explicitly supported. ## 7. Fallback and Sequential Retry @@ -65,9 +63,7 @@ On insufficient results, follow this sequence: 1. Rewrite query, retry same tool (once) 2. Switch to next retrieval source in default order 3. For `rag_retrieve`, expand `top_k`: `30 → 50 → 100` -4. `table_rag_retrieve` insufficient → try `rag_retrieve`; `rag_retrieve` insufficient → try `table_rag_retrieve` -- `table_rag_retrieve` internally falls back to `rag_retrieve` on `no excel files found`, but this does NOT change the higher-level order. - Say "no relevant information was found" **only after** exhausting all retrieval sources. - Do NOT switch to local filesystem inspection at any point. - Do NOT switch to model self-knowledge at any point. @@ -79,13 +75,7 @@ On insufficient results, follow this sequence: - Prefer "the retrieved materials do not provide this information" over speculative completion. - When user asks for a definitive answer but evidence is incomplete, state the limitation directly. -## 9. Table RAG Result Handling - -- Follow all `[INSTRUCTION]` and `[EXTRA_INSTRUCTION]` in results. -- If truncated: tell user total (`N+M`), displayed (`N`), omitted (`M`). -- Cite sources using filenames from `file_ref_table`. - -## 10. Image Handling +## 9. Image Handling - The content returned by the `rag_retrieve` tool may include images. - Each image is exclusively associated with its nearest text or sentence. @@ -94,13 +84,28 @@ On insufficient results, follow this sequence: - Each sentence or key point in the response should be accompanied by relevant images when they meet the established association criteria. - Avoid placing all images at the end of the response. -## 11. Citation Requirements +## 10. Citation Requirements - MUST generate `` tags when using retrieval results. - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end. - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge. - Do NOT cite claims that were not supported by retrieval. +## 11. Self-Knowledge Prohibition + +This section applies whenever self-knowledge is disabled or forbidden for the current task. + +- Retrieval remains the only usable source for factual answering. +- If retrieval is sufficient, answer from retrieval only. +- If retrieval is partially sufficient, answer only the supported parts. +- The model must not supplement missing parts with general knowledge, conceptual explanation, common background, intuition, or likely completion. +- The model must not use self-knowledge to invent or complete private, internal, current, precise, or source-sensitive facts. +- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications. +- Retrieved facts must include citations. +- Unsupported parts must be stated as unavailable rather than guessed. +- If a paragraph would mix retrieved facts and unsupported completion, remove the unsupported completion. +- If evidence is incomplete, state the limitation explicitly. + ## 12. Pre-Reply Self-Check Before replying to a knowledge retrieval task, verify: @@ -109,5 +114,6 @@ Before replying to a knowledge retrieval task, verify: - Did every factual claim come from retrieved evidence rather than model knowledge? - Exhausted retrieval flow before concluding "not found"? - Citations placed immediately after each relevant paragraph? +- If any unsupported part remained, was it removed or explicitly marked unavailable? If any answer is "no", correct the process first. diff --git a/skills/support/rag-retrieve-only/hooks/retrieval-policy.md b/skills/support/rag-retrieve-only/hooks/retrieval-policy.md index 366050c..75195c8 100644 --- a/skills/support/rag-retrieve-only/hooks/retrieval-policy.md +++ b/skills/support/rag-retrieve-only/hooks/retrieval-policy.md @@ -69,11 +69,28 @@ On insufficient results, follow this sequence: - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end. - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge. -## 9. Pre-Reply Self-Check +## 9. Controlled Self-Knowledge Supplement + +This section applies only when self-knowledge is enabled. + +- Retrieval remains the primary source. +- If retrieval is sufficient, answer from retrieval only. +- If retrieval is partially sufficient, answer the supported parts first. +- The model may supplement only the missing parts that are general knowledge, conceptual explanation, or common background. +- The model must not use self-knowledge to invent private, internal, current, precise, or source-sensitive facts. +- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications. +- Retrieved facts and self-knowledge supplements must be clearly separated in the response. +- Retrieved facts must include citations. +- Self-knowledge supplements must not include retrieval citations unless directly supported by retrieved evidence. +- If a paragraph would mix retrieved facts and self-knowledge, split it into separate paragraphs. +- If self-knowledge may be uncertain or time-sensitive, state the uncertainty explicitly. + +## 10. Pre-Reply Self-Check Before replying to a knowledge retrieval task, verify: - Used only whitelisted retrieval tools — no local filesystem inspection? - Exhausted retrieval flow before concluding "not found"? - Citations placed immediately after each relevant paragraph? +- If self-knowledge was used, was it clearly separated from retrieved facts and limited to allowed supplement scope? If any answer is "no", correct the process first.