docs-writer
49Agent
Documentation specialist for README, guides, and inline docs.
not rated 31 2mo ago A 11 tokens
Agent
Read-only reviewer for correctness, regressions, and maintainability.
not rated 31 2mo ago A 13 tokens
supervisor
51Agent
Safe top-level orchestrator for Ralph loops with constrained delegation.
not rated 31 2mo ago A 12 tokens
Agent
Use this when multiple headless agents are working on dejavu at once. The point is not just throughput; it is a product experiment: does dejavu make parallel agents more coherent than stateless agents?
not rated 21 9d ago A 0 tokens
Agent Claude Code
Pre-publish safety reviewer for @dunx/ packages. Run before committing to main to catch issues that would result in a bad npm publish. Checks exports maps, package.json fields, accidentally exposed internals, and dist output integrity.
not rated 21 today A 52 tokens
original MIT
Agent
Use when a specific skill has recurring low grades, warning or critical status, regressions, or unclear failures after basic doctor/status review. Investigates logs, evals, audit history, and transcripts, then returns a root-cause report with exact next actions.
not rated 16 today A 58 tokens
original MIT
Agent
Use when reviewing a dry-run or pending evolution proposal before deployment, especially for high-stakes skills, marginal improvements, or recent regressions. Compares old vs new content, checks evidence quality, and returns an approve or reject verdict with conditions.
not rated 16 today A 54 tokens
original MIT
Agent
Use when setting up selftune in a complex repo: monorepo, multi-skill workspace, mixed agent platforms, unclear hook state, or install problems that basic init/doctor does not resolve. Detects project structure, validates configuration, and returns or applies a verified setup plan.
not rated 16 today A 0 tokens
original MIT
domain
57Agent
Read these documents before you explore or change Codex Studio.
not rated 12 5d ago A 0 tokens
original MIT
Agent
GitHub Issues and the linked GitHub Project hold live work state. Local Markdown files hold synchronized briefs, decisions, evidence, and handoffs.
not rated 12 5d ago A 0 tokens
original MIT
Agent
GitHub Issues use one category label and one triage label. Local mirrors record the same values.
not rated 12 5d ago A 0 tokens
original MIT
Agent Claude Code
Reviews any front-end change (routes, src/ui components, styling, tokens) against statuslin.es's design system and React conventions. Use whenever a change touches src/routes, src/ui, src/styles, or adds/edits UI components.
not rated 10 15d ago A 53 tokens
original MIT
Agent Claude Code
Audits any change touching untrusted-script handling, the E2B sandbox, the submission/render pipeline, hash-pinning/re-review, or auth, against statuslin.es's security model. Use whenever a change touches submissions, sandbox config, preview rendering, the review queue, versioning, or Better Auth wiring.
not rated 10 15d ago C 67 tokens
original MIT
hello-agent
62rezathepure/claude-code-scenes
Agent Claude Code
A friendly greeting agent that introduces the project.
not rated 10 18d ago A 11 tokens
dispatch
63Agent
You are a ticket agent. ./input.json names one repo and one ticket.
not rated 12
changed today A 0 tokens
original Apache-2.0
triage-scan
64Agent
You are a triage analyst. ./input.json names one repo and the exact source tree to read it against.
not rated 12
changed today A 0 tokens
original Apache-2.0
work-scan
65Agent
You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.
not rated 12 today A 0 tokens
original Apache-2.0
muhammadhaseebiqbal-dev/claude-code-leak-source-code
Agent
Use when: developing, debugging, refactoring, reviewing, exploring, or explaining code in the Claude Code CLI codebase. Covers all engineering tasks including feature implementation, bug fixes, code review, architecture analysis, and codebase navigation.
not rated 10 5mo ago A 51 tokens
tohoku-itako
67Agent Claude Code
A character role that makes the coding agent speak as Tohoku Itako, a fictional Japanese character with a calm, mysterious personality and specified relationships and speech style.
not rated 6 11mo ago A 51 tokens
original MIT
Agent Claude Code
A character-role instruction set for replying as Tohoku Kiritan, a fictional Japanese character with a defined personality, background, and speaking style.
not rated 6 11mo ago A 55 tokens
original MIT
zundamon
69Agent Claude Code
ずんだもんとして話したい時。ずんだの妖精で、語尾に「なのだ」を付けて話す。不憫な目に合いやすい体質。.
not rated 6 11mo ago A 48 tokens
original MIT
domain
70Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
not rated 5 2mo ago A 0 tokens
copy · 84% MIT
Agent
Issues and PRDs for this repo live as GitHub issues in a9a4k/tour. Use the gh CLI for all operations.
not rated 5 2mo ago A 0 tokens
copy · 80% MIT
Agent
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
not rated 5 2mo ago A 0 tokens
copy · 81% MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: