sonnet

sonnet is an Agent task delegation & fan-out skill for AI agents, published by jellyrock in the jellyrock repository on GitHub. Skillspace rates sonnet D (64/100) and it passed the safety scan; the rating is based on static analysis only.

Execute a procedural implementation plan saved at `.claude/plans/focus-YYYY-MM-DD-slug.md` using the Sonnet model for token savings. Invoked as `/sonnet <plan-path>`, or by a parent agent after `/focus` surfaces an ad-hoc quick-fix hand-off block. Reads the plan top-to-bottom, applies the edits using JellyRock's canonical npm wrappers (`npm run validate`, `npm run test:scripts`, `npm run test:tdd`, `npm run lint`), runs the plan's Verification gates, surfaces a commit proposal, and stops before push for explicit user OK. NOT for judgment-heavy work — if the plan still has open forks, architectural decisions, or "we need to figure out X" gaps, stay on Opus and finish the planning side first via `/focus`. NOT for investigation/recipe work that already has a dedicated skill (`/ci-triage`, `/issue-triage`, `/new-setting`, …) — the recipe is the better plan.

Grade
D
Quality
64 / 100
Safety
Passed
GitHub stars
35

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubjellyrock/jellyrock

Our review

Architecture
100 / 100
Maturity
Basic: a single SKILL.md
Security scan
Low-risk patterns
License
GPL-2.0
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Agent task delegation & fan-out

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.