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/codehub-code-packnpx skills add theagenticguy/opencodehub --skill codehub-code-packgit 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 | $0.00152 | $0.02495 |
| Opus 5 | $0.00076 | $0.01247 |
| Sonnet 5 | $0.00030 | $0.00499 |
| Haiku 4.5 | $0.00015 | $0.00249 |
Grade A, and why
codehub-code-pack 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codehub-code-pack
Surface the pack_codebase MCP tool to a Claude Code agent. Produces a
deterministic, 9-item Bill of Materials (BOM) at <repo>/.codehub/packs/<packHash>/
that is byte-identical given the same (commit, tokenizer, budget, chonkie_version, grammar_commits). The pack is the
durable artifact agents hand to long-context LLMs, archive in S3 for
later replay, or diff between commits to prove invariants did not
change.
Purpose
The 9-item BOM is the smallest faithful representation of a repo for
LLM consumption: a manifest pinning every input that could change
output, a PageRank-ranked skeleton (top symbols first), a file tree,
a dependency lockfile slice, AST-chunked top files, SCIP-grounded
cross-refs, an optional embeddings Parquet sidecar, salient SARIF
findings, and a LICENSES + README pair. Determinism is the headline
property: re-running with identical inputs MUST produce identical
output bytes (verified by cmp -s and the determinism suite — see
references/determinism-contract.md).
packHash is sha256(canonicalJson(manifest_with_packHash_omitted)) —
it commits to every other field in the manifest, including the
fileHash of every BOM item. Two packs share a packHash iff every
input that the pack emitter looked at is identical.
When to use this skill vs pack_codebase --engine repomix:
- Use this skill when the user wants reproducibility, archival, a pack to feed to a CI replay job, or a pack to compare across commits. Default for any "pack the repo" request unless the user explicitly asks to skip determinism.
- Use
pack_codebase --engine repomix(no skill required) when the user wants a one-shot bandwidth-saving dump for a single LLM call and explicitly does not need byte-identity. The repomix path remains opt-in through M6 then sunsets in M7.
Single-repo mode
- Pre-check — call
list_repos. If the target repo is not indexed, instruct the user to runcodehub analyzeand stop. If≥ 2repos are indexed and norepoargument was supplied, the per-repo tool will returnAMBIGUOUS_REPO; retry with one of thestructuredContent.error.choices[].repo_urivalues verbatim (Sourcegraph-style URI, e.g.github.com/org/repo, orlocal:<hash>). - Confirm graph freshness — call
project_profileon the resolved repo. If the response carries a_meta.codehub/stalenessenvelope, surface it: tell the user the pack will reflect the lastcodehub analyzerun, not HEAD. - Optional findings preview — if the user asks for findings in
the pack, call
list_findingsto confirm SARIF rows exist. - Pack — call
pack_codebasewithengine: "pack"(the default). The tool resolvesoutDirto<repoRoot>/.codehub/packs/<packHash>/and writes the 9 items plusmanifest.json. - Report back — surface the
packHash, thedeterminismClass, and the absolute output directory. IfdeterminismClassisbest_effortordegraded, name the cause (Anthropic tokenizer rotation hazard, or chonkie native binding unavailable).
What ships with it
1 file 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 · 182 lines · 152 tokens per session scan A 7317cc94ca69
codehub-code-pack is a skill published in the GitHub repository theagenticguy/opencodehub (3 stars, last pushed 20d ago), licensed Apache-2.0. It adds 152 tokens to every session and 2,495 once invoked, about $0.0008 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…