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 agentmods add skills/greglas75/zuvo/content-migrationnpx skills add greglas75/zuvo --skill content-migrationgit clone --depth 1 https://github.com/greglas75/zuvoWhat 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 | $0.00094 | $0.04945 |
| Opus 5 | $0.00047 | $0.02472 |
| Sonnet 5 | $0.00019 | $0.00989 |
| Haiku 4.5 | $0.00009 | $0.00494 |
Grade A, and why
content-migration scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Neither → `MODE=degraded` (curl, warn about JS content). How it starts
The opening of the file, as written. The whole thing — 480 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:content-migration — CMS-to-SSG Content Parity Check & Fix
Compare an old CMS page with its new SSG version. Report parity gaps. Optionally apply safe additive patches to the local markdown source.
One page pair per invocation. For bulk progress, use --status.
Out of scope: SEO optimization (zuvo:seo-audit), content hygiene
(zuvo:content-audit), pixel-level visual comparison, redirect mapping.
Mandatory File Loading
Read before work begins:
../../shared/includes/env-compat.md-- Environment adaptation../../shared/includes/live-probe-protocol.md-- Consent + rate limiting
Load on demand:
../../shared/includes/codesift-setup.md-- Only if source file needs discovery../../shared/includes/migration-fix-registry.md-- Only with--fix../../shared/includes/verification-protocol.md-- Only with--fix../../shared/includes/run-logger.md-- At report phase../../shared/includes/retrospective.md-- At report phase
Safety Gates
GATE 1 — Consent
Per live-probe-protocol.md for BOTH --old and --new URLs.
GATE 2 — Read-Only Default
Without --fix: compare and report only. Writes only to zuvo/reports/.
GATE 3 — Conservative Fixes
With --fix:
- Never delete content from the new site
- Never reorder existing content
- Never modify files not explicitly resolved as the source
- Dirty file check:
git status --porcelain -- <file>. Dirty → STOP. - If insertion point is ambiguous →
NEEDS_REVIEW, do not guess - All fixes are additive (insert missing content only)
- Limit: max 5 content insertions per run. When many gaps found, prefer report-first over bulk insertion.
Arguments
| Argument | Behavior |
|---|---|
--old <url> |
Original CMS page URL (required, unless --status) |
--new <url> |
New SSG page URL or localhost (required, unless --status) |
--fix |
Apply fixes to local .md file (default: compare only) |
--source-file <path> |
Explicit path to the .md file for --new page |
--settle-ms <ms> |
Wait after page load (default: 3000, max: 15000) |
--scroll-to-bottom |
Scroll page before extraction (triggers lazy-loaded content) |
--content-selector <sel> |
CSS selector for content area (default: auto-detect) |
--wait-for <sel> |
Wait for specific element before extraction |
--status |
Show migration progress dashboard (no --old/--new needed) |
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.
- 2d ago First seen · 480 lines · 94 tokens per session scan A 23ea58c615e5
content-migration is a skill published in the GitHub repository greglas75/zuvo (6 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 4,945 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
ring:writing-plans
Writing a rolling-wave phased implementation plan from a spec before coding: a phase-epic-task hierarchy where Phase 1 is detailed into dispatch-ready tasks and later phases stay epic-level for elaboration during execution. Use when a multi-file feature needs decomposition; runs after ring:exploring-codebases or…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:generating-release-guides
Generating an internal Operations-facing update/migration guide from the git diff between two refs, documenting per-change client impact, deploy ordering, monitoring, and rollback notes in English, pt-br, or both. Use when preparing a version release or recording what changed for the Ops team. Runs read-only by…
ring:writing-skills
Writing or editing a Ring skill: SKILL.md structure, frontmatter and Agent-Search-Optimization rules, token-efficiency targets, and bulletproofing (Iron Law, rationalization tables, Red Flags) so discipline-enforcing skills resist excuses. Use when creating or revising a skill. Delegates pressure-testing to…