agentleFS
Grzanka99Grzanka99/skills/sol-loop/SKILL.md

sol-loop

Skill1 starsChanged 4 months agoNo licenceView on GitHub

Use when the user says "sol loop".

13 other projects use a version of this, 8 of them edited; 5 of 6 edited versions we compared changed its rules; 5 new projects in the last 4 weeks, against 1 the 4 before.

How people change it

5 of 6 edited versions changed its rules, and some changes recur.

Of the 6 edited versions we compared: 1 keep every rule, 5 made changes of their own.

Rules people drop

  1. If T3 tools are not listed, try one direct capability call. Outside T3, use a native Sol subagent and keep its ID. In Claude Code, use a custom subagent only if it is set up to run Sol. If no route runs Sol, report the blocker. Do not substitute a model.dropped by 4 of 5
  2. Start one only if budget remains and a blocker or should is open, behavior code changed, or approval does not cover the current behavior diff. Use a fresh delegate_task in T3, or follow up the saved native ID. …dropped by 2 of 5
  3. Default: 3 rounds total. Round 1 is full. Later rounds check only changed code and open findings.dropped by 1 of 5
  4. Run git status --short. Do not stash, discard, or include unrelated changes. Limit review to the change paths if they separate cleanly. Otherwise stop and ask.dropped by 1 of 5
  5. Use one diff command all rounds. State intent and out-of-scope in 1-2 sentences. Run covering checks. Do not send code this change breaks. Note missing or pre-failing checks in the brief.dropped by 1 of 5
  6. Do not edit scoped files while review runs. Wait for the notice. Do not poll or start a second reviewer. Timeout, error, or no reply is not approval. On failure, cancel, verify stop, restart with the ledger.dropped by 1 of 5
  7. Check each finding and severity yourself. Another path, rare case, or small cost is a nit, whatever label it came with.dropped by 1 of 5
  8. Update the ledger. Re-run checks and git diff --shortstat <base>. If review grew the diff, cut first. Do not agree just to end the loop.dropped by 1 of 5

Rules people add

  1. If no available model is Sol, report the blocker. Do not substitute a model.added by 2 of 5

We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.

Adopted by

Surging: 5 new projects took it in the last 4 weeks, 5× the 4 weeks before.thin data

Week of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 1 new projectWeek of Oct 18: 1 new projectWeek of Oct 25: 2 new projectsWeek of Nov 1: 2 new projectsWeek of Nov 8: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 6 in all, so this is a hint, not a trend.

Most recently taken up by

Used with

Projects with it also use takeover.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • assisjpSkill

    takeover

    Take over an existing branch, pull request, worktree, or agent handoff while preserving the original goal, contributor credit, and concurrent work. Use when the user asks to take over, finish, rescue, or continue someone else's implementation. Do not use to replace a clear request to start new work.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

12 rules. 8 are common, 1 is distinctive, and 3 are very specific to this project.

  • 8

    Common

    Most of the 9 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.