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/multikernel/branching/integrationnpx skills add multikernel/branching --skill integrationgit clone --depth 1 https://github.com/multikernel/branchingWhat 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 | $0.00000 | $0.01935 |
| Opus 5 | $0.00000 | $0.00967 |
| Sonnet 5 | $0.00000 | $0.00387 |
| Haiku 4.5 | $0.00000 | $0.00194 |
Grade A, and why
integration 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(["agent", "--workdir", str(b.path)], check=True) How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
branching — Copy-on-Write Workspace Branching for AI Agents
Explore multiple strategies without consequences. Fork the workspace into parallel copy-on-write branches, run speculative attempts in each, commit the winner, and abort the rest — instantly.
Workspace
A workspace is a directory backed by BranchFS, a copy-on-write FUSE filesystem. All branching operations happen within a workspace.
Prerequisite: The workspace must be mounted before use:
branchfs /mnt/workspace
The CLI auto-detects the workspace from your current directory if you are
inside a branchfs mount. Otherwise pass -w /mnt/workspace.
CLI
branching run — single branch execution
Run a command in an isolated branch. Commits on exit 0, aborts on non-zero.
branching run -- ./build.sh
branching run --ask -- make test # prompt before commit/abort
branching run --on-error none -- python train.py # keep branch on failure
branching run --memory-limit 512M -- ./agent.sh
branching speculate — race N approaches
Race multiple commands in parallel. First success wins, rest are aborted.
Use when multiple approaches could work and you want the fastest success.
branching speculate -c "./fix_a.sh" -c "./fix_b.sh" -c "./fix_c.sh"
branching speculate --timeout 60 -c "python v1.py" -c "python v2.py"
branching best-of-n — parallel with scoring
Run the same command N times in parallel. Commit the highest-scoring success.
Child writes score to fd 3 (echo 0.95 >&3). Gets BRANCHING_ATTEMPT env var.
Use when quality matters: pick the best result across multiple attempts.
branching best-of-n -n 5 -- ./solve.py
branching best-of-n -n 3 -- bash -c 'python run.py && echo "$SCORE" >&3'
branching reflexion — retry with feedback
Sequential retry with critique. Child gets BRANCHING_ATTEMPT and
BRANCHING_FEEDBACK (empty on first try, critique output on retries).
Use when failure output helps improve the next attempt.
What ships with it
3 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 · 259 lines · 0 tokens per session scan A e1015b35f094
integration is a skill published in the GitHub repository multikernel/branching (22 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,935 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…