fable-new-issue-loop
Skill50 starsChanged 5 days agoMITView on GitHub
Use when the user asks to have a Fable 5.1 subagent draft and file a GitHub issue, then autonomously drive it all the way to a reviewed PR in one shot — "fable-new-issue-loop", "fable create the issue and run it to completion". Runs fable-new-issue to create a fully-specified issue (drafted by a Fable 5.1 subagent), then hands the new issue's `owner/repo#N` reference to validate-issue-loop (validate → update → work-on-issue-loop) — stopping instead when a duplicate is found or the discussion hasn't converged on one issue.
In this repository39 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- app-prdSkill
- cli-dispatchSkill
- codex-validate-plan-work-on-issueSkill
- create-releaseSkill
- execution-plan-reviewSkill
- expo-app-initializeSkill
- fable-advisorSkill
- fable-dispatchSkill
- fable-new-issueSkill
- fable-orchestrateSkill
- fableplan-loopSkill
- fableplanSkill
- fableplan-work-on-issueSkill
- fable-validate-fableplan-loopSkill
- fable-validate-fableplanSkill
- fable-validate-loopSkill
- fable-validateSkill
- fix-pr-review-loopSkill
- fix-pr-reviewSkill
- github-issue-formatSkill
- issueplanSkill
- milestoneplanSkill
- milestone-workflowSkill
- new-app-pipelineSkill
- new-issue-loopSkill
- new-issueSkill
- prd-questionsSkill
- prd-to-issuesSkill
- pr-reviewSkill
- sync-docs-releaseSkill
- sync-docsSkill
- tldrSkill
- validate-fableplan-loopSkill
- validate-issue-loopSkill
- validate-issueSkill
- wansSkill
- work-on-issue-loopSkill
- work-on-issueSkill
The file
Files
fable-new-issue-loop
Chain fable-new-issue → validate-issue-loop into one autonomous run: a Fable 5.1 subagent drafts the issue, the main agent files it, and the loop drives it to a reviewed PR without a human in between.
This skill is new-issue-loop with a different front of the chain. Follow the new-issue-loop skill for the full procedure: the complete-issue rule, the input contract, the stop gate, the handoff to validate-issue-loop (always the explicit owner/repo#N reference), the ownership of the plan: yes signal, the report format, and the Red Flags. Apply only the deltas below.
Deltas from new-issue-loop
- Step 1, front of the chain. Invoke the
fable-new-issueskill (Skill tool,skill: fable-new-issue) in place ofnew-issue. Let it run its full process (Fable 5.1 subagent draft, duplicate gate, spot-check, filing) and capture the created issue from its report asowner/repo#Nper new-issue-loop step 1. - Step 2, stop gate. new-issue-loop's stop gate applies with one extra row for the Fable draft; the effective table:
| Condition | Action |
| fable-new-issue found an existing open issue/PR already covering it (no issue filed) | STOP. Report the duplicate and the offer to update/comment instead; do not merge scopes yourself. |
| The conversation held several distinct candidates | If one clearly converged, file it and continue the chain with it; the unfiled candidates go in the final report. If none clearly converged, STOP — report the candidates and ask which to file. Never bundle, never auto-file the extras. |
| fable-new-issue split the work and named unfiled follow-ups | Continue with the core issue only; relay the unfiled follow-ups in the final report. |
| The draft was structurally wrong and fable-new-issue paused for a human decision | STOP. Relay what is off. Do not file or re-dispatch on your own. |
The drafting dispatch failed a second time on the Agent path (fable-dispatch section 7) | STOP. Relay the failure report. Do not re-dispatch, and do not draft or file the issue yourself. |
| The section 7 snapshot diff shows that the drafting subagent wrote | STOP. Relay the changed paths. Do not revert them, file, or continue on that tree; the user decides. |
- Step 4, report. Mark the issue line as drafted by the model that served, as
fable-new-issuerecorded it (Fable 5.1 when Fable served). Cap the whole report at 55 words and 5 sentences, plain simple English in ASD-STE100 — apply the Response Style rules in CLAUDE.md/AGENTS.md. - One extra Red Flag. Tempted to skip the Fable subagent and draft or file the issue yourself to go faster: never.
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
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.