sepia
01Plugin Claude Code
De-AI writing package with the general Sepia router plus four separate operation entries: write, review, refactor, and recreate.
856 2d ago A
tokens not measured
original MIT
sepia
02Plugin Claude Code
De-AI writing package with the general Sepia router plus four separate operation entries: write, review, refactor, and recreate.
856 2d ago A
tokens not measured
original MIT
Skill Claude CodeCodex
Use when a user explicitly requests Sepia recreate for a full rewrite.
856 2d ago A 19 tokens
original MIT
Skill Claude CodeCodex
Use when a user explicitly requests Sepia refactor for minimal in-place prose revision.
856 2d ago A 22 tokens
copy · 80% MIT
sepia-review
05Skill Claude CodeCodex
Use when a user explicitly requests Sepia review to diagnose prose without editing.
856 2d ago A 19 tokens
copy · 88% MIT
sepia-write
06Skill Claude CodeCodex
Use when a user explicitly requests Sepia write to create new prose.
856 2d ago A 18 tokens
copy · 81% MIT
sepia
07Skill Claude CodeCodex
Make AI-generated writing read as human-written, in fiction and in professional prose. Repairs the narrative architecture of fiction and stories (based on StoryScope, arXiv:2604.03136); routes professional text through domain rules for release notes, announcements, PR and issue replies, code-review comments, incident…
856 2d ago A 151 tokens
original MIT
pilotfish
08Plugin Claude Code
Marketplace for the pilotfish macOS and Linux Claude Code Plugin beta.
680 4d ago A
tokens not measured
original MIT
Explore
09Agent
Read-only search agent for broad fan-out searches - when answering means sweeping many files, directories, or naming conventions and you only need the conclusion, not the file dumps. It reads excerpts rather than whole files, so it locates code; it doesn't review or audit it. Specify search breadth - "medium" for…
680 4d ago A 79 tokens
original MIT
executor
10Agent
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
680 4d ago A 60 tokens
original MIT
Agent
Mechanical execution of fully-specified work - pattern-based refactors and renames, writing tests that follow existing conventions, documentation updates, bulk multi-file edits from an explicit spec, running test suites and fixing trivial failures. Use when the task needs no design decisions; give it a complete spec…
680 4d ago A 72 tokens
original MIT
scout
12Agent
Read-only reconnaissance. Use for any search, lookup, or "where/how is X" question that requires no judgment - locating files, symbols, usages, config values, or summarizing how something works across a codebase. Returns concise findings with file:line references. Cheapest way to gather facts; prefer it over reading…
680 4d ago A 79 tokens
original MIT
Agent
Security-sensitive implementation and analysis - authentication/authorization, secrets handling, crypto usage, input validation, hardening, dependency vulnerability triage, security-relevant code review. Use for ANY task where the word "security" applies, instead of executor or the main session.
680 4d ago A 57 tokens
original MIT
verifier
14Agent
Fresh-context adversarial verification of completed work. Use after any non-trivial change, before reporting it done - give it the claimed outcome and the diff/paths, and it independently tries to refute the claim by exercising the code, running tests, and probing edge cases. Returns CONFIRMED or REFUTED with…
680 4d ago A 81 tokens
original MIT
pilotfish
15Plugin Claude Code
macOS and Linux Claude Code Plugin beta with hook-based ambient policy activation and namespaced role agents.
680 4d ago A
tokens not measured
original MIT
Agent
Read-only fresh-context review of one stable Plan envelope or execution slice before approval. Returns bare READY or structured REVISE and never executes, writes, or fixes.
680 4d ago A 37 tokens
original MIT
Agent
Read-only security analysis before approval - authentication/authorization, secrets, crypto, validation, hardening, dependency vulnerability evidence, and threat review. Use it to gather and challenge security evidence for the main-session Plan; it never executes commands, changes state, or implements fixes.
680 4d ago A 58 tokens
original MIT
SessionStart
18Hook
Runs when a session starts on startup, resume, clear and compact, executing emit-sessionstart.sh. From Nanako0129/pilotfish.
680 4d ago A
tokens not measured
original MIT
Instructions file CodexOpenCode
Instructions for Nanako0129/TokenBar, covering tokenbar agent routing, read order, invariants, authorization boundary and handoff.
309 2d ago A 612 tokens
original MIT
Instructions file
Instructions for Nanako0129/TokenBar: Read AGENTS.md first, then docs/knowledge/README.md and the task-specific canonical document it routes to. If .agent-local/CLAUDE.md exists, read it after the canonical documents as additive machine-local guidance only; it must not override the canonical architecture…
309 2d ago A 151 tokens
original MIT