Candor — Security skill for Claude Code
Twelve anti-sycophancy work-mode personas for Claude Code - direct, verification-driven, benchmarked.
How to install Candor
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open itsryanlenk/candor and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Candor does
Twelve anti-sycophancy work-mode personas for Claude Code - direct, verification-driven, benchmarked. Coding, debug, security, architecture, writing, data, curation, and more. MIT.
Alternatives in Security
- Mcp-scan (Invariant Labs) — MCP security scanner with proxy mode for real-time scanning without infrastructure changes 1.9k ★
- Pocketpaw — Your AI agent in 30 seconds 775 ★
- Maestro Odyssey — Long-running iterative cycle — one entry, seven modes (debug improve planex review security defensive ui) 530 ★
README
**Anti-sycophancy behavioral modes for Claude Code.** A small plugin that swaps flattery, hedging, and "this should work" for directness, verification, and per-task efficiency - and switches its style to fit the kind of work you're doing.
[](LICENSE) ![Status: experimental]() 
What it is
Candor is a Claude Code [plugin](https://code.claude.com/docs/en/plugins) containing twelve [skills](https://code.claude.com/docs/en/skills): one shared anti-sycophancy **core**, and eleven **work-mode personas** that tune Claude's behavior for the task in front of it. The skills load automatically when they're relevant, and you can also invoke any of them by name.
The goal is narrow and practical: reduce the specific, measurable ways an RLHF-trained assistant becomes _less useful_ - reflexive agreement, hollow praise, caving under pushback without new evidence, padding, false balance, and claiming success without checking - while keeping it genuinely helpful. Candor is **not** an instruction to be harsh; a whole section of the core skill exists to keep directness from tipping into manufactured contrarianism.
The twelve skills
| Skill | When it engages | Persona / disposition |
|---|---|---|
| candor-core | Always- |
Related Skills
Deep
Execute the current task using DEEP mode for architecture, security, data, infrastructure, public contracts, o
Skill Quality Research
Craft-first quality review for Agent Skill repos — an LLM judges how well a skill is WRITTEN (trigger design,
Project Init Skill
A Claude Code skill that runs a 3-round project kickoff interview before writing any code — outputs full archi
Audit MCP Mock Drift
Catch mock/live divergence in MCP eval golden tests (anti-pattern #2 from eval-mock-mode-discipline)
Academic Paper Accuracy And Citation Audit
Use when: (1) performing a multi-pass LaTeX paper audit covering data consistency, cross-references, scientifi
Security Gate
Security verification for G4 — verify allocated controls actually exist and work, triage scanner output, produ
Related Agents
Anti Slop Editor
Audit PR descriptions, commit messages, code comments, and documentation to eliminate AI slop, conversational
UX Researcher
User research specialist who creates personas, maps user journeys, validates design decisions, and ensures fea
Metadata Application Discovery Agent
Inventory ALL metadata-driven applications across a tree of Vert.x metadata modules by parsing every MAPL() re
