ramboz

34 mods across 1 repository, 6 stars between them.

jig

01

ramboz/jig

Plugin Claude Code

Plugin marketplace listing 1 plugin: jig.

6 yesterday A tokens not measured original MIT

jig

02

ramboz/jig

Plugin Claude Code

Spec-driven, review-enforced, hook-gated AI-native development workflow for Claude Code.

6 yesterday A tokens not measured original MIT

architect

03

ramboz/jig

Agent Claude Code

../../agents/architect.md.

6 yesterday A 0 tokens original MIT

implementer

04

ramboz/jig

Agent Claude Code

../../agents/implementer.md.

6 yesterday A 0 tokens original MIT

reviewer

05

ramboz/jig

Agent Claude Code

../../agents/reviewer.md.

6 yesterday A 0 tokens original MIT

PreToolUse

06

ramboz/jig

Hook Claude Code

Runs before the agent uses a tool for Task, Skill, Edit, Write, MultiEdit and Read tool calls, executing jig-telemetry.sh, jig-skill-trace.sh, jig-spec-gate.sh, jig-secret-scan.sh and jig-context-check.sh via bash (5 commands). From ramboz/jig.

6 yesterday A tokens not measured copy · 50% MIT

PostToolUse

07

ramboz/jig

Hook Claude Code

Runs after a tool call finishes for Edit, Write, MultiEdit and AskUserQuestion tool calls, executing jig-post-edit-verify.sh, jig-boundary-change-warn.sh, jig-entry-gate.sh and jig-decision-inflight.sh via bash (4 commands). From ramboz/jig.

6 yesterday A tokens not measured copy · 52% MIT

SessionStart

08

ramboz/jig

Hook Claude Code

Runs when a session starts, executing jig-context-check.sh, jig-project-orient.sh, jig-semantic-index.sh and jig-git-freshness.sh via bash (5 commands). From ramboz/jig.

6 yesterday A tokens not measured copy · 45% MIT

UserPromptSubmit

09

ramboz/jig

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing jig-memory-scan.sh, jig-context-check.sh and jig-decision-inflight.sh via bash (3 commands). From ramboz/jig.

6 yesterday A tokens not measured copy · 47% MIT

Stop

10

ramboz/jig

Hook Claude Code

Runs when the agent finishes a response, executing jig-task-capture.sh, jig-decision-capture.sh and jig-claim-check.sh via bash (3 commands). From ramboz/jig.

6 yesterday A tokens not measured original MIT

jig

11

ramboz/jig

Settings file Claude Code

Agent settings declaring 5 hook events (PreToolUse, PostToolUse, SessionStart, UserPromptSubmit).

6 yesterday A tokens not measured copy · 86% MIT

jig AGENTS.md

12

ramboz/jig

Instructions file CodexOpenCode

Instructions for ramboz/jig, covering jig — ai-native dev scaffold, hot cache, project codenames / active work, key terms (one-line index — full defs via /jig:explain ) and key documents.

6 yesterday A 2,947 tokens original MIT

jig CLAUDE.md

13

ramboz/jig

Instructions file

Instructions for ramboz/jig, covering jig — ai-native dev scaffold, hot cache, project codenames / active work, key terms (one-line index — full defs via /jig:explain ) and key documents.

6 yesterday A 3,756 tokens original MIT

jig

14

ramboz/jig

Plugin Claude Code

Spec-driven, review-enforced, hook-gated AI-native development workflow for Claude Code.

6 yesterday A tokens not measured copy · 100% MIT

adr-workflow

15

ramboz/jig

Skill Claude CodeCodex

Scaffold, accept, index, and link Architectural Decision Records (ADRs). Use when the user says "write an ADR", "record this decision", "resolve [deferred item] with an ADR", "supersede ADR-NNNN", or otherwise wants to capture a hard-to-reverse decision in docs/decisions/. Also use when a refinement-todo entry needs…

6 yesterday A 122 tokens original MIT

analyze

16

ramboz/jig

Skill Claude CodeCodex

Cross-artifact consistency report for jig specs — a non-destructive six-category audit at CRITICAL/HIGH/MEDIUM/LOW severity, covering duplication, ambiguity, underspecification, principle violations, coverage gaps, and terminology drift. Auto-triggers when you say analyze this spec, check for inconsistencies, audit…

6 yesterday A 160 tokens original MIT

arch-review

17

ramboz/jig

Skill Claude CodeCodex

Team baseline for architecture, design-doc, and RFC review — produces summary, strengths, concerns, and open questions. Auto-triggers when you say review this design, review this architecture, review this proposal, review my RFC, poke holes in this proposal, is this design sound, or critique this tech spec. Defers to…

6 yesterday A 207 tokens original MIT

bug-fix

18

ramboz/jig

Skill Claude CodeCodex

Drive the teeth-gated lifecycle for reported defects: diagnose root cause, prove it, and prevent regression through REPORTED → DIAGNOSING → ROOTCAUSED → FIXING → REVIEWED → DONE, with VERIFIED, ESCALATED, and RESOLVEDONMAIN paths where needed. Auto-fires on fix this bug, debug this, root-cause this, this regressed…

6 yesterday A 208 tokens original MIT

clarify

19

ramboz/jig

Skill Claude CodeCodex

Lightweight spec clarification scan for jig projects — a six-category ambiguity audit that asks up to five prioritized questions and appends them to the spec's ## Clarifications section. Auto-triggers when you say clarify this spec, audit this spec for ambiguities, is this spec ready for review, find unknowns in this…

6 yesterday A 153 tokens original MIT

code-health

20

ramboz/jig

Skill Claude CodeCodex

Run a static-analysis pass on a project — detect the ecosystem (Python or Node), drive its linter (ruff / eslint, plus advisory pyright/complexity/ prettier and a cross-ecosystem duplication signal) via the health.py helper, and act on the normalized exit code (0 clean / 1 findings / 2 no-linter). Auto-triggers when…

6 yesterday A 230 tokens original MIT

contracts

21

ramboz/jig

Skill Claude CodeCodex

Team baseline for external-interface contract artifacts: OpenAPI, JSON Schema, AsyncAPI, .proto, and GraphQL SDL, with spectral, ajv, buf, and graphql-inspector validation. Nudges devs toward contract-first artifacts; never writes them and never scaffolds a contracts/ directory. Auto-triggers for what contract should…

6 yesterday A 163 tokens original MIT

explain

22

ramboz/jig

Skill Claude CodeCodex

Explain jig vocabulary and artifacts in plain language. Three modes: term mode defines one lexicon term; artifact mode walks through a spec or ADR and its linked references; passage mode explains pasted jig output. Output is ephemeral (chat-only). Auto-triggers when you say explain this term, walk me through this…

6 yesterday A 173 tokens original MIT

independent-review

23

ramboz/jig

Skill Claude CodeCodex

Build the standardized prompt for a fresh reviewer subagent that evaluates implemented work against its spec without access to the implementation conversation. Use after an implementer subagent completes a spec slice (when the slice is ready for REVIEWED), or after a deviation log is written (for reconciliation…

6 yesterday A 96 tokens original MIT

memory-sync

24

ramboz/jig

Skill Claude CodeCodex

Persist new context, terms, learnings, and settled lightweight decisions. Use when the user says remember this, save this for later, add to glossary, note this down, or at session end to consolidate what was learned — that goes to the memory layer (CLAUDE.md hot cache, docs/memory/, docs/inbox.md). Also use to record…

6 yesterday A 228 tokens original MIT