Catalog
Every x402, MPP, MCP, and skill listing we've indexed, normalized, and enriched.
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.
shared-system-init-shape-parity
Centralize system init or capability payload construction in one builder so multiple transports emit identical schemas and only vary inputs or delivery.
session-memory-mailbox-exclusion
Prevent session-memory background forks from draining teammate mailbox attachments that belong to the main lead thread.
session-memory-first-compaction
Attempt session-memory compaction before full conversation compaction so lightweight summaries win when available.
semantic-theme-key-rendering
Resolve semantic theme keys into terminal-safe colors with contextual overrides before rendering text.
seed-before-diff-marketplace-registration
Register seeded extension sources before diffing materialized state so bootstrap content is treated as present instead of missing.
scrollback-freeze-optimization
Cache and reuse animated children once they slide into scrollback so terminal resets never occur.
safe-worktree-slug-validation
Ensure Git worktree slugs can never escape the managed workspace or inject traversal.
role-aware-context-slimming
Trim user and system context based on the agent\u2019s role so read-only helpers don\u2019t inherit stale git or CLAUDE metadata.
resume-skill-listing-suppression
Mark the current skill listing as already sent when resuming so the transcript does not receive a redundant payload.
reserved-summary-output-budget
Reserve part of the context window for summary output so proactive compaction does not kill the response budget.