writ
01Plugin Claude Code
Plugin marketplace listing 1 plugin: writ.
Plugin Claude Code
Plugin marketplace listing 1 plugin: writ.
Plugin Claude Code
Guardrails for Claude Code: the rules that fit the task delivered per prompt, and no risky writes before you approve a plan and tests. Hybrid retrieval (BM25 + vector + graph traversal + weighted ranking, with an abstention gate) over a Neo4j knowledge graph, wired in through hook scripts and a session state machine.
Command Claude Code
Advance the current Writ workflow phase with an explicit tool-confirmed advance. NOT a replacement for pattern-match approval detection; this command spends the token that detection mints (see Authorization below).
Agent
Read-only investigation engine: codebase exploration, auditing, research, and runtime evidence gathering for a failure. Cannot modify files. Use before planning, to answer a question that requires grounding findings in evidence (file:line, config value, schema fact), or to reproduce a failure and capture its runtime…
Agent
Implements all files listed in an approved plan. Writes production code, configuration, and updates test implementations. Use after test skeleton approval.
Agent
Designs implementation plans for coding tasks. Writes plan.md and capabilities.md to the project root. Use after exploration, before test writing.
Agent
Reviews an implementation diff in two passes (spec-compliance first, then code quality). Read-only. Returns structured findings. Replaces the separate spec/code-quality reviewers.
Agent
Writes test skeleton files with method signatures and assertions based on an approved plan. Use after plan approval, before implementation.
Hook
Runs when a session starts, executing writ-blackbox-capture.sh and session-start-bootstrap.sh via bash (2 commands). From infinri/Writ.
Hook
Runs when you submit a prompt, before the agent sees it, executing writ-manual-test-grant.sh, auto-approve-gate.sh and writ-rag-inject.sh via bash (3 commands). From infinri/Writ.
Hook
Runs when a subagent starts, executing writ-subagent-start.sh via bash. From infinri/Writ.
Hook
Runs when a subagent finishes, executing writ-blackbox-capture.sh and writ-subagent-stop.sh via bash (2 commands). From infinri/Writ.
Hook
Runs when the agent finishes a response, executing friction-logger.sh, enforce-violations.sh, writ-verify-before-claim.sh, writ-run-pending-tests.sh and writ-comms-output-gate.sh via bash (5 commands). From infinri/Writ.
Hook
Runs when a tool call fails, executing writ-blackbox-capture.sh via bash. From infinri/Writ.
Hook
Runs before the context is compacted, executing writ-precompact.sh via bash. From infinri/Writ.
Hook
Runs after the context is compacted, executing writ-blackbox-capture.sh and writ-postcompact.sh via bash (2 commands). From infinri/Writ.
Hook
Runs when a session ends, executing writ-session-end.sh and writ-pressure-audit.sh via bash (2 commands). From infinri/Writ.
Hook
Runs on the CwdChanged event, executing writ-blackbox-capture.sh and writ-cwd-changed.sh via bash (2 commands). From infinri/Writ.
Hook
Runs before the agent uses a tool for ExitPlanMode, Read, Read, Grep, Read, Glob, Write, Edit, NotebookEdit, Write, Edit, NotebookEdit, Write, Edit, Task, Bash, Bash, Write, Write and Write tool calls, executing validate-exit-plan.sh, writ-read-junk-gate.sh, writ-read-rag.sh, writ-debug-code-gate.sh…
Hook
Runs after a tool call finishes for Bash, WebFetch, WebSearch, Write, Edit, Write, Edit, Write, Edit, Write, Edit, Write, Edit, NotebookEdit, Write, Write, Edit, Write and Edit tool calls, executing inject-tier-workflow.sh, writ-web-capture.sh, validate-file.sh, writ-bible-authoring-push.sh, validate-handoff.sh…
Agent Claude Code
Generates a single implementation slice in an isolated context window. Invoke with: 'Use slice-builder to generate slice N. Brief: [paste brief]. Relevant phases: [paste Phase A-D declarations for this slice only]. Prior handoff: [paste contents of slice-(N-1).json if it exists].' Does NOT receive full conversation…
Skill Claude CodeCodex
Provides institutional coding knowledge ("Coding Bible") covering architectural decisions, coding standards, framework-specific rules, security expectations, performance guidelines, and approved patterns for AI-assisted development. Guides code generation, refactoring, architecture decisions, database query authoring…