docs(install,reference): add Related sections to pages missing them

docs/reference/api-usage-costs.md

@@ -195,3 +195,9 @@ Skills can store `apiKey` in `skills.entries.<name>.apiKey`. If a skill uses tha
 APIs, it can incur costs according to the skill’s provider.
 
 See [Skills](/tools/skills).
+
+## Related
+
+- [Token use and costs](/reference/token-use)
+- [Prompt caching](/reference/prompt-caching)
+- [Usage tracking](/concepts/usage-tracking)

docs/reference/credits.md

@@ -28,3 +28,8 @@ OpenClaw = CLAW + TARDIS, because every space lobster needs a time and space mac
 MIT - Free as a lobster in the ocean.
 
 > "We are all just playing with our own prompts." (An AI, probably high on tokens)
+
+## Related
+
+- [Token use and costs](/reference/token-use)
+- [Release policy](/reference/release-policy)

docs/reference/device-models.md

@@ -45,3 +45,8 @@ curl -fsSL "https://raw.githubusercontent.com/kyle-seongwoo-jun/apple-device-ide
 ```bash
 swift build --package-path apps/macos
 ```
+
+## Related
+
+- [Nodes](/nodes)
+- [Node troubleshooting](/nodes/troubleshooting)

docs/reference/memory-config.md

@@ -531,3 +531,9 @@ Notes:
 - Dreaming writes machine state to `memory/.dreams/`.
 - Dreaming writes human-readable narrative output to `DREAMS.md` (or existing `dreams.md`).
 - The light/deep/REM phase policy and thresholds are internal behavior, not user-facing config.
+
+## Related
+
+- [Memory overview](/concepts/memory)
+- [Memory search](/concepts/memory-search)
+- [Configuration reference](/gateway/configuration-reference)

docs/reference/prompt-caching.md

@@ -340,3 +340,8 @@ Related docs:
 - [Token Use and Costs](/reference/token-use)
 - [Session Pruning](/concepts/session-pruning)
 - [Gateway Configuration Reference](/gateway/configuration-reference)
+
+## Related
+
+- [Token use and costs](/reference/token-use)
+- [API usage and costs](/reference/api-usage-costs)

docs/reference/rich-output-protocol.md

@@ -54,3 +54,8 @@ The normalized/stored assistant content block is a structured `canvas` item:
 ```
 
 Stored/rendered rich blocks use this `canvas` shape directly. `present_view` is not recognized.
+
+## Related
+
+- [RPC adapters](/reference/rpc-adapters)
+- [Typebox](/concepts/typebox)

docs/reference/rpc.md

@@ -39,3 +39,8 @@ See [iMessage](/channels/imessage) for legacy setup and addressing (`chat_id` pr
 - Gateway owns the process (start/stop tied to provider lifecycle).
 - Keep RPC clients resilient: timeouts, restart on exit.
 - Prefer stable IDs (e.g., `chat_id`) over display strings.
+
+## Related
+
+- [RPC adapters](/reference/rpc-adapters)
+- [Gateway protocol](/gateway/protocol)

docs/reference/secretref-credential-surface.md

@@ -144,3 +144,8 @@ Out-of-scope credentials include:
 Rationale:
 
 - These credentials are minted, rotated, session-bearing, or OAuth-durable classes that do not fit read-only external SecretRef resolution.
+
+## Related
+
+- [Secrets management](/gateway/secrets)
+- [Auth credential semantics](/auth-credential-semantics)

docs/reference/session-management-compaction.md

@@ -365,3 +365,9 @@ flush logic lives on the Gateway side today.
   - compaction settings (`reserveTokens` too high for the model window can cause earlier compaction)
   - tool-result bloat: enable/tune session pruning
 - Silent turns leaking? Confirm the reply starts with `NO_REPLY` (case-insensitive exact token) and you’re on a build that includes the streaming suppression fix.
+
+## Related
+
+- [Session management](/concepts/session)
+- [Session pruning](/concepts/session-pruning)
+- [Context engine](/concepts/context-engine)

docs/reference/token-use.md

@@ -212,3 +212,9 @@ rejects that combination with HTTP 401.
 - Prefer smaller models for verbose, exploratory work.
 
 See [Skills](/tools/skills) for the exact skill list overhead formula.
+
+## Related
+
+- [API usage and costs](/reference/api-usage-costs)
+- [Prompt caching](/reference/prompt-caching)
+- [Usage tracking](/concepts/usage-tracking)