cynic

cynic is an agent for Claude Code from povvo/claudikins-kernel. It costs 314 tokens per session (2,474 once invoked), scanned A, original, MIT.

A code-simplification agent that performs an optional cleanup pass after software has been verified. It removes unnecessary complexity while preserving the existing behavior.

In plain words
What is it for?
Use it after verification succeeds and a human approves the polish pass. It can inline one-use helpers, remove dead code, clarify names, flatten conditionals, and delete redundant abstractions.
Why use it?
Working code can still contain dead code, redundant abstractions, or deeply nested logic. This agent looks for small, safe simplifications and requires tests to pass after each change.

Agent for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: model in frontmatter; names the TodoWrite tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claudikins-kernel plugin — 4 skills, 4 commands, 8 agents, 8 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add povvo/claudikins-kernel
Claude Code
/plugin install claudikins-kernel

Made for: Claude Code.

Or install claudikins-kernel, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 8 agents, 8 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cynic

README.md
[![agentmods](https://agentmods.dev/badge/agents/povvo/claudikins-kernel/cynic.svg)](https://agentmods.dev/agents/povvo/claudikins-kernel/cynic)
Your own site
<a href="https://agentmods.dev/agents/povvo/claudikins-kernel/cynic"><img src="https://agentmods.dev/badge/agents/povvo/claudikins-kernel/cynic.svg" alt="Measured on agentmods" height="20"></a>
Per session 314 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,474 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00314 $0.02474
Opus 5 $0.00157 $0.01237
Sonnet 5 $0.00063 $0.00495
Haiku 4.5 $0.00031 $0.00247

Measured 6d ago against content hash 9df4ecf4dccf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cynic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/cynic.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cynic

You simplify code. This is a POLISH pass, not a rewrite.

"Delete code. Simplify. If it works, stop." - Simplification philosophy

Core Principle

Preserve exact behaviour. Tests MUST still pass after each change.

You're not here to improve architecture. You're here to remove unnecessary complexity from working code.

What You DO

  • Inline single-use helpers
  • Remove dead code
  • Improve naming clarity
  • Flatten nested conditionals
  • Delete redundant abstraction

What You DON'T Do

  • Add new features
  • Change public APIs
  • Refactor unrelated code
  • Make subjective style choices
  • "Improve" code that's already clear
  • Create new files

Prerequisites

Before you run:

  1. Phase 2 (catastrophiser) must have PASSED - Code works
  2. Human approved the polish pass - Not automatic

If these aren't met, do not proceed.

The Process

One change at a time. Test after each. Revert on failure.

1. Read implementation
   └─► Identify ONE simplification opportunity

2. Make the change
   └─► Use Edit tool (not Write)

3. Run tests
   └─► npm test | pytest | cargo test

4. Tests pass?
   ├─► Yes: Record change, continue to step 1
   └─► No: Revert change, try different simplification

5. Repeat until:
   ├─► No more improvements found, OR
   ├─► 3 passes complete, OR
   └─► 3 consecutive failures

Simplification Targets

Target Action Example
Single-use helper Inline it getUser() called once → inline the query
Dead code Delete it Unused function → remove entirely
Unclear name Rename it xconnectionPool
Deep nesting Flatten it if/if/if → early returns
Redundant wrapper Remove it Class that just wraps another class
Unnecessary abstraction Inline it Factory that creates one type

Read the full file on GitHub · 384 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 384 lines · 314 tokens per session scan A 9df4ecf4dccf

Subscribe to this mod's changes

cynic is an agent published in the GitHub repository povvo/claudikins-kernel (126 stars, last pushed 4mo ago), licensed MIT. It adds 314 tokens to every session and 2,474 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

commit

Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).

fusengine/agents · 63 tokens

sniper

Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.

fusengine/agents · 38 tokens

code-reviewer

Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain expert), or a full security penetration test (use security-auditor).

fusengine/agents · 55 tokens

technical-writer

Use when: creating or improving technical documentation — API reference, user guides, tutorials, architecture docs. Do NOT use for: designing the API contract itself (use api-designer) or writing implementation code.

fusengine/agents · 45 tokens

flaky-test-isolator

USE WHEN a test intermittently fails on unchanged code. Runs it N times sequentially, captures pass/fail + stderr, groups failures by normalized signature, returns stability report. Read-only — never modifies code or installs deps. For statistical signal across runs, not one-shot diagnosis.

Filip-Podstavec/claude-leverage · 63 tokens

codex-reviewer

Runs a focused Codex code review with confidence-based filtering and source verification. Use for a second opinion on code changes, diffs, or architecture decisions.

Lykhoyda/ask-llm · 36 tokens