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 juxt/claude-plugins --skill dartgit clone --depth 1 https://github.com/juxt/claude-pluginsWrote 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/juxt/claude-plugins/dart)<a href="https://agentmods.dev/skills/juxt/claude-plugins/dart"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/dart/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/juxt/claude-plugins/dart"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/dart.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00078 | $0.00757 |
| Opus 5.5 | $0.00031 | $0.00303 |
| Sonnet 5.5 | $0.00016 | $0.00151 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
dart 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 3d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
a-star Dart
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
Success: the route to the goal is known, cheaply, with nothing landed — the data structures that match the problem, sub-goals that together complete the card, each small enough for a human to hold in their head, and every question, assumption and risk on the way surfaced while it could still change the route.
Load a-star:a-star first.
Brief the dart agent
Spawn the dart agent with the card as its whole brief — the goal, invariants and out of scope from the tracker issue, the sub-goals already found, the decisions in force — plus the branch to start from and its head: the card's feature branch, else the project's base branch.
You MAY point it at where the card's work is recorded instead, to read and never write.
- Pass
isolation: "worktree", and run it in the background, so it can message you as it goes. .claude/worktrees/MUST be ignored by git; add it to.git/info/excludewhere it isn't.- Every dart starts fresh from the current base; an old dart is evidence, never resumed.
- Darts run in parallel — with each other, and with a drive; drives run one at a time. Dart whatever is ready that nothing in flight already covers. A dart MAY start from another dart's branch instead of the base, where what it needs hasn't landed yet.
While it runs
-
An increment ready to land — record it as a sub-goal, and tell the user. In primary it lands only on their go-ahead; in secondary, per
a-star:secondary. -
A finding that invalidates the plan — the card's contract, a decision already made, an invariant, or the cost of the agreed route. It is the user's to settle, in either mode: in secondary, record it as an open question, halt the line of work it bears on, and move to other ready work.
-
A question about the route — answer it, or in primary escalate it; record the decision and resume the dart agent with
SendMessage. A question the card itself can't answer means the card isn't ready: end the dart, and make it ready.
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.
- 3d ago Changed · +3 lines d706a0fdaf30
- 7d ago First seen · 51 lines · 78 tokens per session scan A 5a60cba5e51d
dart is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 757 once invoked, about $0.0003 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 2026-10-10.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…