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/mpolatcan/codehub/release-cutnpx skills add mpolatcan/codehub --skill release-cutgit clone --depth 1 https://github.com/mpolatcan/codehubWhat 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 | $0.00054 | $0.00888 |
| Opus 5 | $0.00027 | $0.00444 |
| Sonnet 5 | $0.00011 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
release-cut 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 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.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut a CodeHub release
Pre-flight required:
- Working tree clean on
main TEST_SCENARIOS.mdregression checklist (the end-of-doc list) has been walked manuallycargo checkclean insidesrc-tauri/npm run buildclean- Docker Hub credentials available for
ghcr.io/mpolatcan/codehub-runtime
1. Bump version everywhere
The version appears in four places. Update all to the same value (X.Y.Z):
package.json—"version": "X.Y.Z"src-tauri/Cargo.toml—version = "X.Y.Z"under[package]src-tauri/tauri.conf.json—"version": "X.Y.Z"src-tauri/src/lib.rs—const DEFAULT_IMAGE: &str = "ghcr.io/mpolatcan/codehub-runtime:X.Y.Z";
Commit the version bump as its own commit: chore: bump version to X.Y.Z.
2. Publish the runtime image
From repo root, after the version bump in step 1 is committed:
make image-push # multi-arch buildx push (linux/amd64, linux/arm64)
The image-push target reads the tag from src-tauri/src/lib.rs:DEFAULT_IMAGE and also retags :latest.
Verify the manifest after push:
docker buildx imagetools inspect ghcr.io/mpolatcan/codehub-runtime:X.Y.Z
Both linux/amd64 and linux/arm64 platforms must be listed.
3. Build the desktop bundles
make build
Outputs land in src-tauri/target/release/bundle/:
- macOS:
dmg/CodeHub_X.Y.Z_aarch64.dmgand/or_x64.dmg - Linux:
deb/codehub_X.Y.Z_amd64.deb,appimage/codehub_X.Y.Z_amd64.AppImage
On macOS, repeat the build inside an x86_64 host (or use --target x86_64-apple-darwin) if you want a universal release. Sign + notarize with xcrun notarytool before publishing if you have a developer ID.
4. Tag + push
git tag -a vX.Y.Z -m "CodeHub X.Y.Z"
git push origin vX.Y.Z
5. GitHub release
gh release create vX.Y.Z \
--title "CodeHub X.Y.Z" \
--notes-file CHANGELOG-NEXT.md \
src-tauri/target/release/bundle/dmg/*.dmg \
src-tauri/target/release/bundle/appimage/*.AppImage \
src-tauri/target/release/bundle/deb/*.deb
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 · 97 lines · 54 tokens per session scan A c1c40f691c32
release-cut is a skill published in the GitHub repository mpolatcan/codehub (5 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 888 once invoked, about $0.0003 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
rmux
Guide for using RMUX with Claude Code, including the tmux-compatible CLI, agent automation waits, the typed SDK, browser web-share, and the rmux claude launcher.
dstest
Deterministic simulation testing for containerized services. Write Lua scripts to inject chaos (pause, kill, resource deprivation) into Docker containers with reproducible, seeded fault injection. Use when writing chaos experiments, testing service resilience, or debugging distributed systems.
dokan
Operate the dokan runtime — run deterministic scripts in Docker over MCP, compose DAG flows, schedule cron, set secrets, return structured results, read logs token-frugally. Use when the user wants to run/deploy a script or job, build a pipeline/flow/DAG of steps, schedule recurring work, provision API keys for a job…
m07-concurrency
CRITICAL: Use for concurrency/async. Triggers: E0277 Send Sync, cannot be sent between threads, thread, spawn, channel, mpsc, Mutex, RwLock, Atomic, async, await, Future, tokio, deadlock, race condition, 并发, 线程, 异步, 死锁.
core-agent-browser
Internal support skill for agent-browser CLI workflows used by rust-learner, docs-researcher, and crate-researcher. Use only when browser automation is explicitly required.
domain-cli
Use when building CLI tools. Keywords: CLI, command line, terminal, clap, structopt, argument parsing, subcommand, interactive, TUI, ratatui, crossterm, indicatif, progress bar, colored output, shell completion, config file, environment variable, 命令行, 终端应用, 参数解析.