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/evoelsewhere/evoflux/coding-migrationnpx skills add evoelsewhere/evoflux --skill coding-migrationgit clone --depth 1 https://github.com/evoelsewhere/evofluxWhat 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 | $0.00074 | $0.00927 |
| Opus 5 | $0.00037 | $0.00464 |
| Sonnet 5 | $0.00015 | $0.00185 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
coding-migration 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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate a code system
Make each migration stage independently deployable, observable, and reversible until evidence proves the old path can be removed. Do not load bundled references when this skill activates.
Inventory the transition
- Identify current and target contracts, producers, consumers, persisted data, deployment units, generated artifacts, and ownership boundaries.
- Determine which components can upgrade atomically and which cannot. Include older clients, delayed jobs, replayed events, rollback versions, and data written during the compatibility window.
- Define invariants that must hold in mixed-version operation.
- Read references/expand-contract-playbook.md for a compatibility matrix and phase gates when the transition spans deployments, stored data, or multiple repositories.
When a migration surface is known only by behavior, package, schema term, or
protocol text, call code_context with action="search" once across authorized repositories to find
its declared boundary. Skip it when the exact identifier is already known.
For every exact API, type, event, schema adapter, or migration entry-point
symbol, use code_context to establish direct references/callers and
bounded impact before sequencing rollout. Start at depth 1; preserve
repository identity and treat dynamically unresolved cross-repository references as an inventory
gap, not as absence of consumers. Once an exact boundary is selected, make the
graph the next structural observation instead of continuing broad discovery.
Keep refresh=true for the first indexed query and after edits. Use refresh=false only for an immediate follow-up that intentionally reuses the same index version.
Read references/code-context-contract.md only after a result exposes ambiguity, cross-repository traversal, truncation, or dynamic-wiring limits.
Choose and sequence a strategy
Select the smallest safe strategy: expand/contract, adapter, dual read, dual write, backfill, feature-gated cutover, shadow traffic, or atomic replacement. State why its failure modes are acceptable here.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 91 lines · 74 tokens per session scan A 92b2ab9201ee
coding-migration is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 74 tokens to every session and 927 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
kane-cli
Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…
control-chrome
Control the user's Chrome browser for tasks that depend on existing Chrome state: tabs, logged-in sessions, or extensions. Prefer purpose-built connectors, APIs, or CLIs when available.
recent-release
Render Rove's recent releases as a self-contained, Rove-styled HTML page (Chinese by default). Reads shipped notes from packages/kobe/CHANGELOG.md + git tags, filters to user-facing changes, and emits one standalone .html file in the claude theme (terracotta on near-black, JetBrains Mono, terminal chrome). Use when…
yutori-scout
Set up continuous web monitoring with Yutori Scouts. Use when the user wants to track news, competitors, product updates, funding rounds, price changes, or any recurring web information.
yutori-computer-use
Run local Mac desktop tasks with Yutori computer use. Use when the user wants to operate macOS apps, websites in a local browser, or cross-app workflows on the visible desktop.
plan-review-triggers
Required reading whenever drafting any multi-step proposal, implementation plan, refactor approach, or response containing file paths and decision points. Use BEFORE writing any response that lists 3+ file paths, 2+ option-tradeoffs, a "Plan:"/"Steps:"/"Concrete changes:" section, or ends with "OK to proceed?" /…