agentsys: Skill for Claude Code

.kiro/skills/enhance-cross-file/SKILL.md

enhance-cross-file is a skill for Claude Code, Kiro from agent-sh/agentsys. It costs 25 tokens per session (859 once invoked), scanned A, original, MIT.

A checker for consistency across coding-agent files, including tools, skills, agents, and workflows. It looks for relationships and conflicts that may be missed when reviewing one file at a time.

In plain words
What is it for?
Use it to inspect an agent or plugin directory and report cross-file mismatches and maintenance problems.
Why use it?
It helps find references to missing agents, tools used but not declared, duplicated rules, contradictory instructions, and unused agents.

Skill for Claude CodeKiro

Written for Claude Code and Kiro: argument-hint in frontmatter, but also installed under .kiro/. Also seen: mentions CLAUDE.md.

This is agent-sh/agentsys's own configuration. It tells Claude Code and Kiro how to work on agentsys itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentsys configures →

Part of the agentsys plugin — 28 skills, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to agent-sh/agentsys. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agent-sh/agentsys/main/.kiro/skills/enhance-cross-file/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/agent-sh/agentsys

Made for: Claude Code, Kiro.

Or install agentsys, the plugin that ships this one along with the rest of its 28 skills, 1 hook.

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 enhance-cross-file

README.md
[![agentmods](https://agentmods.dev/badge/skills/agent-sh/agentsys/enhance-cross-file/github.svg)](https://agentmods.dev/skills/agent-sh/agentsys/enhance-cross-file)
Your own site
<a href="https://agentmods.dev/skills/agent-sh/agentsys/enhance-cross-file"><img src="https://agentmods.dev/badge/skills/agent-sh/agentsys/enhance-cross-file/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for enhance-cross-file

Your own site · 80×15
<a href="https://agentmods.dev/skills/agent-sh/agentsys/enhance-cross-file"><img src="https://agentmods.dev/badge/skills/agent-sh/agentsys/enhance-cross-file.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 859 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00025 $0.00859
Opus 5 $0.00013 $0.00430
Sonnet 5 $0.00005 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured 9d ago against content hash 699cd0232521, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

enhance-cross-file 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 9d 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.

.kiro/skills/enhance-cross-file/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

enhance-cross-file

Analyze cross-file semantic consistency across agents, skills, and workflows.

Parse Arguments

const args = '$ARGUMENTS'.split(' ').filter(Boolean);
const targetPath = args.find(a => !a.startsWith('--')) || '.';

Purpose

Detects issues that span multiple files - things single-file analysis misses:

  • Tools used in prompt body but not declared in frontmatter
  • Agent references that don't exist
  • Duplicate instructions across files (maintenance burden)
  • Contradictory rules (ALWAYS vs NEVER conflicts)
  • Orphaned agents not referenced by any workflow
  • Skill tool mismatches (allowed-tools vs actual usage)

Workflow

  1. Run Analyzer - Execute the JavaScript analyzer to get findings:

    node -e "const a = require('./lib/enhance/cross-file-analyzer.js'); console.log(JSON.stringify(a.analyze('.'), null, 2));"
    

    For a specific path: a.analyze('./plugins/enhance')

  2. Parse Results - The analyzer returns JSON with summary and findings

  3. Report - Return findings grouped by category

The JavaScript analyzer (lib/enhance/cross-file-analyzer.js) implements all cross-file detection. The patterns below are reference documentation.

Detection Patterns

1. Tool Consistency (MEDIUM Certainty)

tool_not_in_allowed_list: Tool used in prompt body but not in frontmatter tools: list

# Frontmatter declares:
tools: Read, Grep

# But body uses:
Use Write({ file_path: "/out" })  # <- Not declared!

skill_tool_mismatch: Skill's allowed-tools doesn't match actual tool usage in skill body

2. Workflow Consistency (MEDIUM Certainty)

missing_workflow_agent: subagent_type: "plugin:agent-name" references non-existent agent

orphaned_prompt: Agent file exists but no workflow references it (may be entry point - check manually)

incomplete_phase_transition: Workflow phase mentions "Phase N" but no corresponding section

3. Instruction Consistency (MEDIUM Certainty)

Read the full file on GitHub · 111 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. 9d ago First seen · 111 lines · 25 tokens per session scan A 699cd0232521

Subscribe to this mod's changes

enhance-cross-file is a skill published in the GitHub repository agent-sh/agentsys (984 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 859 once invoked, about $0.0001 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 skills, from other repositories

refactor

Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.

code-yeongyu/oh-my-openagent · 36 tokens

pre-publish-review

Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…

code-yeongyu/oh-my-openagent · 161 tokens

work-with-pr

Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…

code-yeongyu/oh-my-openagent · 211 tokens

remove-ai-slops

Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.

code-yeongyu/oh-my-openagent · 45 tokens

review-work

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

code-yeongyu/oh-my-openagent · 63 tokens

tech-debt-audit

Thorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, LSP, and language-native tooling. Produces TECHDEBTAUDIT.md with severity, effort estimates, and prioritized fixes. Use when asked for codebase health check, tech debt audit, architecture review, code quality assessment…

code-yeongyu/oh-my-openagent · 127 tokens