Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add urmzd/dotfiles --skill sync-ecosystemgit clone --depth 1 https://github.com/urmzd/dotfilesWrote 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/urmzd/dotfiles/sync-ecosystem)<a href="https://agentmods.dev/skills/urmzd/dotfiles/sync-ecosystem"><img src="https://agentmods.dev/badge/skills/urmzd/dotfiles/sync-ecosystem/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.
<a href="https://agentmods.dev/skills/urmzd/dotfiles/sync-ecosystem"><img src="https://agentmods.dev/badge/skills/urmzd/dotfiles/sync-ecosystem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00101 | $0.01424 |
| Opus 5.5 | $0.00040 | $0.00570 |
| Sonnet 5.5 | $0.00020 | $0.00285 |
| Haiku 4.5 | $0.00010 | $0.00142 |
Grade A, and why
sync-ecosystem 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 1mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ecosystem Sync
Audit one repository for consistency with the rest of the ecosystem and emit a drift report. To push the report back into the canonical skill store, chain with sync-ecosystem-to-chezmoi (or your equivalent).
Usage: /sync-ecosystem <repo-path>
If no path is given, ask which repo to audit before proceeding.
Principle
Ecosystem conventions evolve. This skill does not enumerate them inline -- that list rots. Instead, it runs an audit loop that pulls the current rules from the skills that own each convention, then reports drift between the target repo and those rules.
Audit Loop
1. Establish repo context
Read whatever identity and manifest files the repo has (README, AGENTS.md, llms.txt, language manifest). From these infer:
- Name and description the identity the rest of the ecosystem should agree with
- Repo type library, CLI, service, website, or something else -- dictates which conventions apply
- Language and build system dictates which
scaffold-<lang>skill to consult
Don't assume any specific file is present. Absence of a file is itself a finding.
2. Pull current conventions
For each convention category, consult the owning skill rather than enumerating rules here:
| Category | Owning skill |
|---|---|
| Required project layout | check-project |
| Community-health files (CODE_OF_CONDUCT, SECURITY, issue forms, PR template) | community-health |
| README structure | write-readme |
| AGENTS.md structure | configure-ai |
| llms.txt structure | create-llms-txt |
| CI/release workflow | setup-ci, sync-release |
| Language-specific scaffold | scaffold-<lang> |
| CLI conventions | build-cli |
| Doc-drift (fsrc, command renames, dead links) | sync-docs (delegate, do not re-implement) |
3. Check drift
Run generic drift checks against what you discovered:
- File presence does the repo have every artifact the owning skills require for this repo type?
- Content currency do listed commands, dependencies, and examples match the current manifest and code?
- Cross-reference agreement do name, description, install command, and version agree across docs and manifest?
- Version discipline does the latest git tag match the manifest version (or match the tagging scheme declared by
sync-release)? - Terminology does usage in the repo match the terms used in this ecosystem's other published skills and docs? Flag divergences; do not auto-rewrite.
- Doc subset for the documentation-specific portion of the audit (fsrc drift, dead internal links, stale commands), invoke
sync-docsinstead of re-implementing the checks.
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.
- 1mo ago First seen · 136 lines · 101 tokens per session scan A 8d4af1452d8d
sync-ecosystem is a skill published in the GitHub repository urmzd/dotfiles (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,424 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
pr-review
Intelligent PR code review with dynamic agent allocation based on change types. Analyzes PR changes and generates targeted review tasks.
analyze-pr
Analyze a GitHub/GitLab Pull Request by fetching its diff, reading its web description, and generating a comprehensive document. Use when the user provides a PR link and wants to understand what changes the PR introduces, or asks to review/analyze/summarize a pull request.
review-code
Standalone code review for any scope — PR number, branch, file paths, or current changes. Synthesizes intent, runs 11 parallel specialized agents, and presents actionable findings with a verdict. For PR scope, optionally posts the review to GitHub with inline comments.
review-converge
Autonomously review and fix the current branch or specified scope in iterative rounds until clean, leaving all changes in the working tree. Escalates only genuine design decisions. Ends with a transparent report of every round, every fix, and anything it couldn't resolve.
review-prs
Fetch and present a prioritized summary of all PRs awaiting the current user's review across the relevant projects and provide an interactive workflow helping the user phrase and post inline review comments and overall review decisions.
review-pr-comments-converge
Fetch PR review comments, validate each against the actual code, auto-fix obvious issues, and escalate genuine design decisions. Leaves all changes in the working tree. Use when you want to action reviewer feedback autonomously.