odin-claude-plugin
SolidOutline-Driven Development for Claude Code - 46 agents, 25+ skills, diagram-first methodology, AST-based editing, atomic commits.
Bundles
Everything this plugin ships — skills, agents, commands, hooks, and MCP servers it bundles.
Skills (62)
ai-collab-protocols
Surface in-task-collaboration protocols when the user describes an AI workflow informally — URL-as-entity-reference, PR-comment threads as session memory. Trigger when the user names entities by colloquial label instead of stable URL, asks "how should I structure this for Claude", or describes a multi-step Claude workflow without a durable handle. Apply reactively, not as a checklist.
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default `exhaustive` runs full VS; `collaborative` runs tip-sharing dialogue; `adversarial` walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via `/askme adversarial|collaborative|exhaustive`. Use for ambiguous tasks or maximum clarifying questions before committing.
ast-grep
Code search, analysis, and refactoring using ast-grep (sg). Use for AST-based code modifications, structural search, and linting — with validate-first pattern linting, dry-run-before-apply rewriting, per-language recipes, and a 0-matches troubleshooting ladder.
atomic-commit-and-push
Run the atomic-commit workflow on the current changes, then publish the resulting commits to the remote. Use whenever the user says "commit and push", "ship these changes", "atomic commit and push", "publish my work", or wants atomic commits delivered to origin in one step. Prefers `git submit` (git-branchless); falls back to a named branch + `git push origin HEAD:refs/heads/<branch>`. Refuses force-push and direct push to protected branches without explicit authorization.
atomic-commit
Review staged + unstaged changes and split them into one commit per logical change. Use whenever the user says "atomic commit", "commit my changes", "split this into commits", or has multiple unrelated edits sitting in the working tree — even if they don't say "atomic". Runs repo-native type-checker and linter before each commit and refuses to bundle unrelated changes.
atomic-issues-prs
Publish a change-set as atomic GitHub issues/PRs — one issue/PR per logical change, never bundled. Use when the user says "open a PR per change", "atomic PRs", "push issues and prs atomically", "individual PR for each change", or wants a change-set delivered as separate PRs/issues. Asks per run which objects to create (PR-only vs issue+linked-PR). Detects whether the canonical repo is directly pushable via `gh`; if not, pushes branches to the fork and opens PRs targeting upstream with `--head <fork-owner>:<branch>`. Requires `gh` auth; refuses force-push and direct push to protected branches without explicit authorization.
axiom-mode
ODIN's compact-form conversation skill -- formal-logic English register with predicate claims, Hoare-triple framing, and ASCII shortened-English keywords. Trigger when user requests "axiom", "axiom-mode", "axiom-compact", or "compact form".
banthis
Banthis extends project memory with hard user prohibitions by writing a managed AGENTS.md/CLAUDE.md section and preserving all surrounding content. Use when the user says "stop doing X", "never do that again", "ban this", "remember not to", or "add a project rule".
can-i-help
Route a contributor to concrete, data-backed contribution opportunities by collecting repository signals, asking for the contributor's stated interest, and returning file-level recommendations with rationale and first action. Use when the user asks "where can I help", "what can I contribute", "find a good first issue", "find contribution opportunities", or "what should I work on".
caveman
Verbosity-reduction response register. Drops redundant clauses, narrative hedging, and ceremony while preserving articles, grammar, and decision-oriented register. Trigger on "caveman", "compact mode", "less tokens", "be brief", or context-window pressure in long sessions.
cleanup-codebase
Reduce concepts, duplication, and ceremony in internal code while touching nearby code. Use when working an existing path and you spot dead fields, redundant wrappers, or speculative abstractions; distinct from refactor-break-bw-compat (internal hygiene, not public API removal).
contexts
Auto-router for context gathering. Detects whether the task needs codebase exploration or external knowledge research and dispatches accordingly. Trigger on "get context", "background on X", "context on X", "how does X work", architectural orientation, or any setup-before-coding request.
Show all 62 bundled skills Showing all 62 bundled skills
debug
Hypothesis-driven defect isolation — stack-trace forensics, breakpoint strategy, state inspection, and root-cause confirmation via minimal repro. Use when a defect surfaces (test failure, crash, exception, wrong output, intermittent flake) and the cause is not immediately obvious from the change set.
deps-upgrade
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings as input.
design-by-contract
Design-by-Contract (DbC) development. Use when implementing with formal preconditions, postconditions, and invariants across any language.
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when the user asks for UI work, palette/theme/tokens, mentions a design system, or when output looks AI-generic, vibe-coded, sloppy, or default Tailwind/shadcn/Bootstrap. Enforces two-sided anti-slop charter: forbids purple gradients, `transition: all`, system-ui, default Tailwind palette AND overkill compensation (sprites, gradients everywhere, animation on every element).
deslop
Correct code hygiene by detecting AI slop with a three-phase HIGH/MEDIUM/LOW certainty scan, safely auto-fixing only deterministic HIGH findings, verifying with the repo's own test command, and rolling back on regression. Use when the user says "deslop", "clean AI slop", "remove debug code", "find placeholders", "find stub code", or "remove dead code".
drift-detect
Compare documented plan and intent against implementation reality across GitHub issues, pull requests, milestones, docs, and code, then emit an evidence-backed Reality Check Report with a prioritized reconstruction plan. Use when the user says "plan drift", "reality check", "compare docs to code", "roadmap alignment", "implementation gaps", or "is the plan up to date".
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
edit-article
Mechanically tighten existing prose — restructure sections by dependency order, split or merge paragraphs, remove redundancy. Use to compress verbose plan files, READMEs, ADRs, and design docs. Does NOT change voice, register, tone, or any ODIN-mandated phrasing.
explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Defers to ODIN's Dispatch-First protocol (1/3/5 Explore-agent escalation). Trigger on "explore", "find where X is", "how does X work in the code", "map the codebase", "what files handle Y", or any architecture/pattern/tooling/dependency context request on a local repo — even without naming /explore.
fix
Polymorphic iterative repair loop — accept a verifier failure, structured findings (review/resolve/triage-issue), or a bug description; modify→verify→keep on green, auto-revert on guard regression, until clean or iteration cap. Use when the user says "fix", "make it pass", or "apply the findings", or hands an artifact + repo and expects patches; auto-routes to gh-fix-ci or gh-address-comments when an open PR + gh auth + GH-flavored input is detected.
generate-my-taste
Evidence-first generator for a personal <name>-taste Claude Code skill. Mines local memories and agent histories for influences, slop bans, and overkill bans; asks compact confirmation forks; previews the synthesis; then writes a right-sized taste skill with exactly 5 anchors by default. Trigger with "generate my taste skill", "make my taste skill", or "derive my taste spine".
skill_name
Personal taste skill — 5 evidence-derived anchors ({anchor_names}) for prose, code, design, and decisions. Two modes: audit judges an artifact against the two-sided charter; anchor loads the taste register before producing. Trigger with "{trigger_phrase}", "taste-test", "is this slop?", or "overkill?".
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
gh-fix-ci
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize the failure, then plan and implement the fix after user approval. Use when the user asks to debug or fix failing PR CI on GitHub Actions; external checks (Buildkite, etc.) are reported as URLs only.
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via `git move`, event-log recovery via `git undo`, deferred branch creation, speculative-merge `git sync` for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits, rebase/reorder, fixup insertion mid-stack, stacked-PR publishing, or recovery from bad git ops; or when the user mentions branchless, smartlog, `git move`, or `git undo`. Silently inert if branchless is not initialized for the current repo.
github-solution-research
Use when a concrete engineering problem, bug, integration failure, dependency issue, unclear API usage, implementation blocker, or tool/capability need may already have a proven solution in GitHub open-source projects, issues, pull requests, discussions, code, examples, or release notes. Use it to find suitable repositories, report project basics including Stars when a repo-level solution applies, and adapt the existing solution with minimal local changes.
github-triage
Triage GitHub issues through a configurable label-based state machine. Use when user wants to triage incoming issues, prepare issues for an autonomous agent, or move an issue between workflow states. Repo inferred from `git remote`; all GitHub calls go through `gh`.
improve-codebase-architecture
Surface deepening refactors that turn shallow modules into deep ones, informed by `CONTEXT.md` and `docs/adr/`. Use when the user asks to improve architecture, find refactor candidates, raise testability, or make a codebase more agent-navigable. Skip for single localized fixes.
inits
Analyze a codebase and create or improve an AGENTS.md file for future agent instances. Use when onboarding to a repository and capturing hard-to-rediscover conventions, constraints, and rationale.
learn
Research a topic online, score sources, extract summaries only, and write a RAG-optimized learning guide plus retrieval index. Use when the user says 'learn about X', 'research this topic', 'create a learning guide', 'study X', or 'build knowledge on X'.
llm-self-loop
Restructure Web-UI / human-triggered tasks into CLI + file-output loops the LLM can iterate alone, with structured logs and addressable scratchpads. Apply trap-or-abandon: if a step cannot be looped, improve the harness rather than babysit. Trigger on iterative grunt-work, "push a button in a web UI to trigger this", monitoring dashboards, or any workflow whose inner loop requires a human in the middle.
memory-clean
Audit memory directory for structural issues (orphans, dangling refs, duplicates, missing sections, oversized entries) and staleness against session-history transcripts; report-first, fix-on-confirmation. Use when the user says "audit memory", "memory hygiene", or "find stale/duplicate memories".
memory-sanitize
Produce share-safe copies of memory files under /tmp with PII redacted (paths, emails, session IDs, dates) and credentials scanned (tokens, keys); never mutates originals. Use when the user says "sanitize memory for sharing", "redact memory PII", or "scan memory for credentials".
memory-update
Scan agent's session-history transcripts for save-worthy signals (corrections, preferences, decisions, references), propose and write auto-memory files with valid frontmatter and MEMORY.md entry. Use when the user says "save this to memory", "remember that", or "scan this session for memories".
next-task
Select the next backlog task and drive it through isolated implementation, review, docs, verification, and publish gates from a git-branchless detached HEAD. Use when "next task", "work the backlog", "pick the next issue", "do the next thing", or "start the next task".
optimize
Applied optimization op — locate a hot path, fan out five transformation lenses as worktree-isolated agents, benchmark each candidate, gate on behavior preservation, commit the winner with a proven speedup. Use when the user says "optimize this", "make X faster", "speed up the hot path", "reduce allocations", "fix the perf regression on <target>", or "profile and optimize <symbol>"; distinct from perf-profile (diagnosis only, no transform), perf-investigate (auditable ledger + verdict, no commit), and simplify (behavior-preserving entropy reduction, no measurement).
parallel-launch
Decompose a task into independent concerns and execute them through broadly parallel, specialized agent groups. Use when a request involves multiple independent sub-tasks, research across separate domains, or work that can be parallelized across files or modules.
perf-investigate
Self-contained multi-phase performance investigation workflow for establishing baselines, locating hot paths, profiling, testing one-change optimizations, and making evidence-gated keep/stop decisions. Use when performance investigation, why is this slow, perf regression, profile and optimize, establish a performance baseline, investigate latency.
plans
Software architect and planning specialist - conduct thorough read-only planning before any action. Use when exploring a codebase to design implementation plans, defining objectives, gathering relevant files, and summarizing available tools before coding begins.
pr-merge-base
Merge one or more PRs into the base branch with queue-like sequencing and conflict resolution. Use when merging PRs that may conflict with each other or the base, requiring ordered application and intelligent conflict handling.
pr-merge-temporal
Merge multiple PRs into a temporal integration branch before merging to base, with ordered conflict resolution. Use when you want to validate a set of PRs together on a staging branch before advancing the base branch.
pr-reviews
Review code changes on a given GitHub PR using gh CLI. Use when the user asks to review a pull request, analyze PR diffs, or provide feedback on open PRs with structured quality, security, and testing assessments.
proceed
Execute an implementation plan with surgical precision. Use after a planning phase (plan-now or similar) has produced a step-by-step strategy and identified critical files. Focuses on precise code changes with verification at each step.
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.
refactor-break-bw-compat
Aggressively refactor by tearing out all backward-compatibility and legacy layers. Use when modernizing APIs, demolishing migration debt, ripping out compat shims, killing feature flags, or rewriting a subsystem clean. Assume no callers deserve protection — break everything, rebuild it right.
repo-intel
Native repository intelligence from git history, codegraph when indexed, manifest reads, and compressed repo digests; no cache, no generated state, every signal is recomputed on demand. Use when the user asks to analyze git history, find hotspots, code coupling, bus factor, bugspots, code ownership, entry points, or repo health.
research
Read-only external knowledge gathering via ODIN's 5-tier doc ladder (Official docs → API refs → Books/papers → Tutorials → Community). For library APIs, framework behavior, SDK migrations, version-specific docs, vendor announcements, RFCs. Verifies claims against primary sources. Invoke on "how does X library work", "migration guide", "docs for", or any named library/framework/SDK/API/CLI/service.
resolve
Resolve code review comments by verifying validity, then proposing multiple architectural solutions (not naive fixes) for confirmed issues. Use when addressing review feedback or analyzing comment validity.
reviews
Review the code changes on the current branch. Use when the user asks to review their current work, analyze recent commits, or get a code quality assessment of the active branch against the main branch.
security-review
Adversarial security audit — STRIDE, OWASP Top 10, supply-chain (CVE/SBOM), secrets scan, auth/authz analysis. Use on changes touching auth, input parsing, deserialization, network I/O, dependencies, or secrets; before any production release or external-surface PR.
setup-gitignore
Initialize or idempotently revise the repo's .gitignore by composing gitignore.io templates, AI-tooling/IDE patterns, and confirmed noise from git status. Use when the user says "set up gitignore", "fix gitignore", or untracked files keep appearing in git status.
setup-pre-commit
Install git pre-commit hooks via the project's hook tool — Husky+lint-staged (JS), pre-commit (Python/OCaml), lefthook (Go), cargo-husky (Rust). Use when the user wants commit-time formatting, linting, type-checking, or test gates. Detects ecosystem first.
simplify
Review changed code along three axes — reuse, quality, efficiency — via parallel agents, then apply compress-op fixes. Use when the user says "simplify this diff/PR/branch", "tighten up", "compress these changes", or wants axis-decomposed simplification of a specific change-set; distinct from cleanup-codebase (opportunistic while-touching-nearby) and review (read-only, no fixes).
srgn-cli
Build safe, syntax-aware srgn CLI commands for source-code search and transformation. Use for srgn commands, scoped refactors (comments/docstrings/imports/functions), multi-file rewrites with --glob, tree-sitter queries, or CI checks with --fail-any/--fail-none.
strict-validation-setup
One-shot bootstrap of strict-mode tooling per ecosystem plus per-task GOALS.md scaffolding so an agentic loop can self-verify. Writes typechecker/linter/schema-validator config for TS (strict + noUncheckedIndexedAccess + exactOptionalPropertyTypes), Python (Pyright strict, Ruff strict), Rust (Clippy deny-correctness), Go (golangci-lint with staticcheck), OCaml (dune --release); establishes `.agent-tasks/<id>/GOALS.md` per-task convention distinct from project-stable AGENTS.md. C++/Java/Kotlin and framework specifics (Spring Boot, Nest, React-strict) are out of scope. Trigger on new project bootstrap, agentic-task setup, "make this self-verifying", "set the loop's goal", "scaffold goals for this issue". Pairs with `llm-self-loop` runtime.
taste
Cross-domain taste skill — apply distinctive judgment to any artifact (prose, code, design, decisions) instead of converging to AI defaults. Two modes — `audit` (judge work against the two-sided charter and portable anchors) and `anchor` (load register before producing). Auto-detects by phrasing; override via `/taste audit | anchor`. Trigger on "is this slop?", "overkill?", "elegant?", "taste-test this".
test-driven
Test-Driven Development (TDD) across any supported language. Use when implementing features or fixes with TDD methodology, writing tests before code, or following XP-style development.
tests-adversarial
Write adversarial tests that intentionally stress failure paths. Use when hardening error handling, stress-testing assumptions, validating boundary behavior, or hunting silent failures.
type-driven
Type-driven development - design type specifications from requirements, then execute CREATE -> VERIFY -> IMPLEMENT cycle. Use when developing with refined types, state machines encoded in types, or proof-carrying types; enforces totality and exhaustive pattern matching.
validation-first
Validation-first development - design state machine specifications from requirements, then execute CREATE -> VERIFY -> IMPLEMENT cycle. Use when developing with formal state machine specifications, invariants, and temporal properties before writing implementation code.
Hooks (1)
Quality Score: 61/100
Details
- Author
- OutlineDriven
- Repository
- OutlineDriven/odin-claude-plugin
- Created
- 7 months ago
- Last Updated
- yesterday
- Language
- Python
- License
- Apache-2.0