Catalog
Every x402, MPP, MCP, and skill listing we've indexed, normalized, and enriched.
turn-scoped-memory-prefetch-with-disposal
Start a non-blocking, turn-scoped memory prefetch that auto-disposes and only injects results once per turn.
trusted-frontmatter-gating
Gate frontmatter MCP servers, hooks, and skills behind admin trust when plugin-only or hook-only modes are active.
transport-error-normalization-and-retry-policy
Normalize transport failures into one retry policy so streaming bridges, sockets, and remote clients fail predictably instead of improvising recovery.
tool-success-aware-memory-suppression
Suppress context docs for tools that already succeeded in the current turn while keeping help available for failures or unresolved runs.
token-budgeted-compaction-with-reinjection
Keep compaction budgets under control by compacting incrementally and reinjecting truncated attachments only when the reasoning surface remains stable.
time-gap-cache-expiry-microcompact
When a long idle gap means the server cache is cold, clear old tool-result content before the next request instead of attempting warm-cache cache edits.
time-based-microcompact-trigger
Fall back to time-based microcompaction when the idle gap exceeds the configured threshold and directly clear the oldest compactable tool results.
three-layer-extension-sync
Model extension lifecycle as intent, materialization, and active runtime layers, then sync each layer with dedicated transitions.
terminal-specific-art-fallbacks
Layer terminal detection and fallback fragments so the same mascot identity renders correctly across Apple Terminal, xterm, and other hosts.
telemetry-sanitized-skill-invocation
Record SkillTool usage with sanitized telemetry fields so built-in, bundled, and custom skills are distinguished while avoiding PII leakage.
tail-preserving-task-output-truncation
Persist tool outputs alongside metadata and truncate only the preview, ensuring the header points back to the persisted replica.
subagent-metrics-bridging
Translate a streaming subagent run into task progress, analytics, and notifications while keeping partial results and cleanup tidy.
steady-state-sidecar-sync
Refresh derived sidecar caches even when no primary installs changed so ephemeral runtimes still receive the mirrored state they need.
stall-to-alert-color-escalation
Blend spinner or progress colors toward an alert hue as stall intensity rises so stuck work becomes visually obvious without changing layout.
staged-bundle-fallback-chain
Retry Git bundle creation across decreasing scopes (all, HEAD, squashed) to stay under upload size limits while keeping relevant history.
slash-command-skill-classification-filter
Derive a slash-command skill surface from a broader prompt-command registry by requiring descriptive metadata, excluding builtins, and admitting only a controlled set of origins plus explicit user-only commands.
skip-skill-listing-without-skill-tool
Omit skill-listing attachments for agents that do not expose the Skill tool, so discoverability context is only sent where it can be acted on.
skip-skill-listing-in-test-environment
Suppress skill-listing attachments in test mode so discoverability noise does not interfere with deterministic test behavior.
skip-skill-discovery-on-skill-expansion
Bypass skill discovery when expanded SKILL.md or generated prompt content is being reprocessed for attachments, so non-user text does not trigger recursive discovery work.
skill-scoped-permission-suggestions
Suggest the narrowest permission scope by mapping a file path to its enclosing skill directory before prompting the user.
skill-registry-composition-and-feature-gating
Compose skill registries in fixed phases with explicit feature gates so merged command surfaces stay deterministic and cheap to refresh.
skill-listing-reset-on-real-skill-changes
Reset skill-listing announcement state only when the underlying skill set actually changes, not on compaction or transcript churn.