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.
curl -O https://raw.githubusercontent.com/agent-sh/agentsys/main/.kiro/skills/enhance-orchestrator/SKILL.mdgit clone --depth 1 https://github.com/agent-sh/agentsysWrote 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.
[](https://agentmods.dev/skills/agent-sh/agentsys/enhance-orchestrator)<a href="https://agentmods.dev/skills/agent-sh/agentsys/enhance-orchestrator"><img src="https://agentmods.dev/badge/skills/agent-sh/agentsys/enhance-orchestrator.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.02145 |
| Opus 5 | $0.00014 | $0.01073 |
| Sonnet 5 | $0.00006 | $0.00429 |
| Haiku 4.5 | $0.00003 | $0.00215 |
Grade A, and why
enhance-orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
enhance-orchestrator
Coordinate all enhancement analyzers in parallel and produce a unified report.
Critical Rules
- MUST run enhancers in parallel - Use Promise.all for efficiency
- MUST only run enhancers for existing content - Skip if no files found
- MUST report HIGH certainty first - Priority order: HIGH → MEDIUM → LOW
- NEVER auto-fix without --apply flag - Explicit consent required
- NEVER auto-fix MEDIUM or LOW issues - Only HIGH certainty
Workflow
Phase 1: Parse Arguments
const args = '$ARGUMENTS'.split(' ').filter(Boolean);
const targetPath = args.find(a => !a.startsWith('--')) || '.';
const flags = {
apply: args.includes('--apply'),
focus: args.find(a => a.startsWith('--focus='))?.split('=')[1],
verbose: args.includes('--verbose'),
showSuppressed: args.includes('--show-suppressed'),
resetLearned: args.includes('--reset-learned'),
noLearn: args.includes('--no-learn'),
exportLearned: args.includes('--export-learned')
};
// Validate focus type
const VALID_FOCUS = ['plugin', 'agent', 'claudemd', 'claude-memory', 'docs', 'prompt', 'hooks', 'skills', 'cross-file'];
if (flags.focus && !VALID_FOCUS.includes(flags.focus)) {
console.error(`Invalid --focus: "${flags.focus}". Valid: ${VALID_FOCUS.join(', ')}`);
return;
}
Phase 2: Discovery
Detect what exists in target path:
const discovery = {
plugins: await Glob({ pattern: 'plugins/*/.claude-plugin/plugin.json', path: targetPath }),
agents: await Glob({ pattern: '**/agents/*.md', path: targetPath }),
claudemd: await Glob({ pattern: '**/CLAUDE.md', path: targetPath }) ||
await Glob({ pattern: '**/AGENTS.md', path: targetPath }),
docs: await Glob({ pattern: 'docs/**/*.md', path: targetPath }),
prompts: await Glob({ pattern: '**/prompts/**/*.md', path: targetPath }) ||
await Glob({ pattern: '**/commands/**/*.md', path: targetPath }),
hooks: await Glob({ pattern: '**/hooks/**/*.md', path: targetPath }),
skills: await Glob({ pattern: '**/skills/**/SKILL.md', path: targetPath }),
// Cross-file runs if agents OR skills exist (analyzes relationships)
'cross-file': discovery.agents?.length || discovery.skills?.length ? ['enabled'] : []
};
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.
- 8d ago First seen · 256 lines · 28 tokens per session scan A b5e9144dff32
enhance-orchestrator is a skill published in the GitHub repository agent-sh/agentsys (982 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 2,145 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.
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.
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…
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…
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.
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.
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…