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 skills add martinemde/dotfiles --skill advanced-jjgit clone --depth 1 https://github.com/martinemde/dotfilesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/martinemde/dotfiles/advanced-jj)<a href="https://agentmods.dev/skills/martinemde/dotfiles/advanced-jj"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/advanced-jj/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/martinemde/dotfiles/advanced-jj"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/advanced-jj.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00094 | $0.01070 |
| Opus 5.5 | $0.00038 | $0.00428 |
| Sonnet 5.5 | $0.00019 | $0.00214 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade A, and why
advanced-jj 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 5d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advanced Jujutsu (jj)
Everyday commit flow (describe, new, safety rules) lives in the active
AGENTS.md or equivalent harness instructions.
This skill is the deeper reference — load it when you hit something the
system prompt doesn't cover.
Recipes here were verified against jj 0.38.0 (check jj --version).
Consult jj <command> --help when a command actually fails, or when your
version differs — not by default before acting.
Mental Model
@— the working copy (current change)@-— parent of@- Changes auto-amend: editing files updates
@in place, no staging jj squashfolds@into its parent (--into <rev>targets any ancestor)
Diffs with Filesets
jj show does not accept path arguments — use jj diff. Filesets
support glob and set operations:
jj diff -r @- # full parent diff
jj diff -r @- path/to/file # one file
jj diff -- 'glob:"bin/*" ~ glob:"bin/,special"' # glob minus exclusion
Non-interactive Split
jj split -i needs an editor. For scripted splits, use --tool true
— the true command exits 0, accepting the file list as given:
jj split --tool true -m "Extract feature" -- \
'glob:"path/to/file1"' 'glob:"path/to/file2"'
Remaining changes stay in a follow-up working copy change.
Rebase, Squash, Push
jj rebase takes -o/--onto — not -d/--destination, which older jj
used and models reach for from memory.
jj rebase -r <rev> -o <dest> # one revision onto a destination
jj rebase -s <rev> -o <dest> # revision plus its descendants
jj rebase -b <rev> -o <dest> # whole branch containing <rev>
jj rebase -r <rev> -B <target> # insert before — reorders a stack
jj rebase -r <rev> -A <target> # insert after
jj squash # fold @ into its parent
jj squash --into <rev> # fold @ into any ancestor
jj squash --from <a> --into <b> # move changes between revisions
jj squash --into <rev> --tool true # non-interactive
jj git push -b <bookmark> # one bookmark; new ones push by default
jj git push -c <rev> # push a change, auto-naming its bookmark
jj git push --all --dry-run # preview every push
What ships with it
13 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.
- references/bookmarks.md 11 KB
- references/config.md 63 KB
- references/conflicts.md 7.9 KB
- references/divergence.md 3.5 KB
- references/git-comparison.md 5.6 KB
- references/git-compatibility.md 12 KB
- references/git-to-jj-commands.md 10 KB
- references/github.md 9.4 KB
- references/multiple-remotes.md 3.8 KB
- references/operation-log.md 3.3 KB
- references/revsets.md 24 KB
- references/tutorial.md 23 KB
- references/working-copy.md 5.8 KB
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.
- 5d ago Changed · +16 lines · +13 tokens per session 5ed303e81c9b
- 1mo ago First seen · 90 lines · 81 tokens per session scan A 482ce4af2819
advanced-jj is a skill published in the GitHub repository martinemde/dotfiles (10 stars, last pushed 2d ago), licensed ISC. It adds 94 tokens to every session and 1,070 once invoked, about $0.0004 per session on Opus 5.5. 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
resolve-conflicts
Resolve Git merge or rebase conflicts by both sides' intent; verify the result.
github-pull-request
Open, update, and verify GitHub pull requests.
github-repository
Set GitHub repo description, topics, merge policy, and security settings.
repo-activity
Scan all git repositories under /repos and report recent activity — last commit age, branch, uncommitted changes — in age-bucketed tables. Use when the user asks for a repo activity overview, "what have I been working on", portfolio status, or which repos are active/dormant.
merge-ready
Drive an existing pull request to a mergeable state: get CI green, resolve merge conflicts with the base branch, address and resolve review comments, trigger required bot reviews/approvals (e.g. commenting '@claude review'), link associated issues, and clean up the PR title and description. Ends with a readiness…
sync-release
Owns release-pipeline conventions: sr.yaml schema, the sr CLI verbs (init/plan/prepare/ release) and urmzd/sr action, typed publishers (cargo/npm/pypi/docker/go/custom), monorepo workspace discovery, versionfiles/stagefiles mapping, and post-release patterns. Language-specific build targets live in scaffold-rust…