knitli

34 mods across 2 repositories, 13 stars between them.

ctx-discover

25

knitli/toolshed

Command

Scan the repository and inventory all AI context files across tool ecosystems.

1 4mo ago A 12 tokens original MIT

ctx-drift

26

knitli/toolshed

Command

Find contradictions, gaps, and inconsistencies between AI context files from different tool ecosystems.

1 4mo ago A 16 tokens original MIT

ctx-fix

27

knitli/toolshed

Command

Fix staleness and drift issues found by /ctx:check and /ctx:drift with interactive proposed edits.

1 4mo ago A 23 tokens original MIT

ctx

28

knitli/toolshed

Command

Run a full context hygiene audit: discover all AI context files, check for staleness, and detect cross-tool drift.

1 4mo ago A 24 tokens original MIT

.codex

29

knitli/toolshed

Skill Claude CodeCodex

Skill ".codex" from knitli/toolshed, covering context hygiene skill, name, description, instructions and 1. discovery.

1 4mo ago A 0 tokens original MIT

ctx-audit

30

knitli/toolshed

Cursor rule Cursor

Context hygiene checks when editing or reading AI context files.

1 4mo ago A 0 tokens original MIT

context-hygiene

31

knitli/toolshed

Skill Claude CodeCodex

Knowledge about AI context file locations, staleness patterns, and maintenance rules across 10+ tool ecosystems. Loaded when working with or near context files.

1 4mo ago A 36 tokens original MIT

knitli/toolshed

Plugin Claude Code

Increase agent accountability for results and good decisions. By Jacob Dietle.

1 4mo ago A tokens not measured original MIT

knitli/toolshed

Skill Claude CodeCodex

This skill should be used when making architectural decisions, writing specs, or reviewing decisions that contain "future work", "v2", "simpler for now", "out of scope", or complexity claims. Verifies assumptions are grounded and catches corner-cutting disguised as pragmatism. Applies to code, specs, data models, auth…

1 4mo ago A 77 tokens copy · 92% MIT

strip-ansi

34

knitli/toolshed

Plugin Claude Code

Sanitizes ANSI escape sequences from tool output and detects terminal-based prompt injection attacks (CVE-tagged). Full protection for MCP tools via output replacement; partial protection for built-in tools via context injection.

1 4mo ago A tokens not measured original MIT