anti-tangent-shunt

Claude Code plugin that writes Basic Memory notes per v0.7.0 project-knowledge conventions and the BM v0.21.1 three-step permalink-canonicalization pattern.

14 skills

Four hooks enforcing anti-tangent-mcp's conventions. A PreToolUse hook on Edit/Write/NotebookEdit refuses a dispatched implementer's first edit until validate_task_spec has been called. A PostToolUse hook on TaskUpdate mandates the validate_completion gate at task close, blocks a full-protocol close whose completion ran with no task session, and, when the evidence that call submitted adds comments carrying change history, returns a blocking instruction to reopen and fix — reading the submitted diff, or a final_files completion through git, which reports nothing for work already committed. It detects rather than prevents: PostToolUse fires after the state change. A PreToolUse hook on Edit/Write refuses such a comment before it is written. A PostToolUse hook on Edit/Write/NotebookEdit asks a task once for a check_progress call when it reaches ten edits since validate_task_spec without one; it refuses nothing. Set ANTI_TANGENT_TICKET_PATTERN to your tracker's key shape to have tracker keys caught. Kill switches: ANTI_TANGENT_SESSION_GUARD=0 (start gate and no-session close rule), ANTI_TANGENT_COMPLETION_GUARD=0 (completion gate only), ANTI_TANGENT_COMMENT_GUARD=0 (comment scan, both hooks), ANTI_TANGENT_PROGRESS_GUARD=0 (progress reminder).

hooks

On-demand loader for the anti-tangent-mcp drift-protection protocol. A description-triggered skill that loads only the role-scoped protocol part a task needs, and only when a Goal/Acceptance-criteria task appears — keeping the always-loaded footprint to one line.

1 skill

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server