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/theagenticguy/opencodehub/opencodehub-refactoringnpx skills add theagenticguy/opencodehub --skill opencodehub-refactoringgit clone --depth 1 https://github.com/theagenticguy/opencodehubWhat 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 | $0.00090 | $0.02252 |
| Opus 5 | $0.00045 | $0.01126 |
| Sonnet 5 | $0.00018 | $0.00450 |
| Haiku 4.5 | $0.00009 | $0.00225 |
Grade A, and why
opencodehub-refactoring 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring support with OpenCodeHub
OpenCodeHub's MCP surface is read-only with respect to your source — no tool edits the working tree. This skill uses the graph to plan a refactor (map the blast radius and every reference before you touch anything) and to verify it afterward (confirm the diff matches the plan and nothing unexpected moved). The actual edits are made by you or your editor; OpenCodeHub tells you exactly what to change and then checks your work.
When to Use
- "What will break if I rename
validateUser?" - "Map every caller before I extract this into a module."
- "Where are all the references to this symbol — including dynamic ones?"
- "I just refactored — did the change touch only what I expected?"
- Any rename, extract, split, or move where you need the dependency picture before editing and a verification pass after.
Workflow
PLAN
1. mcp__codehub__impact({ name: target, direction: "upstream" }) → All dependents (the edit list)
2. mcp__codehub__context({ name: target }) → Incoming / outgoing refs + processes
3. mcp__codehub__shape_check (if the symbol is a route/payload) → Producer/consumer drift to watch
4. Build the edit plan from impact's d=1 set + context's refs
APPLY (you / your editor — OpenCodeHub does not do this)
5. Make the edits in your editor or with the language server's rename
VERIFY
6. mcp__codehub__detect_changes({ scope: "unstaged" }) → What the diff actually touched
7. Cross-check changed_symbols against the plan — any surprise is a miss
8. Run tests for the affected processes
If the context envelope warns the index is stale, run
codehub analyzefirst — a stale graph produces an incomplete plan and a misleading verification.
Checklists
Plan and verify a symbol rename
PLAN
- [ ] mcp__codehub__impact({ name, direction: "upstream" }) — enumerate every dependent; this is your edit list
- [ ] mcp__codehub__context({ name }) — see inbound + outbound refs, including ACCESSES edges
(pass `file_path` and/or `kind` to disambiguate when the name is ambiguous)
- [ ] Note the confidenceBreakdown: `unknown > 0` means a heuristic edge the SCIP
oracle contradicted — inspect those by reading source before trusting them
- [ ] Watch for dynamic references the graph cannot see (string-keyed dispatch,
reflection, config JSON, doc comments) — list them as manual-check items
APPLY (your editor / LSP rename — not an OpenCodeHub tool)
- [ ] Apply the rename across the files impact + context named
VERIFY
- [ ] mcp__codehub__detect_changes({ scope: "unstaged" }) — confirm the diff scope
- [ ] Cross-check detect_changes against impact's d=1 count — a gap means a missed reference
- [ ] Run tests for every affected process
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 · 214 lines · 90 tokens per session scan A d7156225edb3
opencodehub-refactoring is a skill published in the GitHub repository theagenticguy/opencodehub (3 stars, last pushed 20d ago), licensed Apache-2.0. It adds 90 tokens to every session and 2,252 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…