fable-status
Skill57 starsChanged 34 days agoMITView on GitHub
Show what oh-my-fable is doing right now, in one table, without changing anything. Plugin version, where the rules live, this session''s mode and why, effort and where it comes from, whether the rules file is current, and CLAUDE.md conflicts. Triggers: "/fable-status", "fable 상태", "규칙 적용됐어?", "지금 뭐가 켜져 있어", "is oh-my-fable active", "fable status", "which rules are loaded", "check the fable setup".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- debabsah/fable-methodtheir own version, first seen Jul 28, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- debabsah/fable-method★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- fable-auditSkill
- fable-setupSkill
- fableSkill
The file
Files
fable-status · what is in effect (read-only)
This skill writes nothing. It answers "is it working, and how?" in one table so the user never has to
inspect files or hook output by hand. Do not run /fable-setup from here; only point to it when a row says so.
Step 1 · One batch of reads
bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh" --status, exactly as written, from the project root (the hook reads the current folder as the project; written this way it runs without a permission prompt). It computes everything: version, config dir, entrypoint, mode, delivery, rules file version, effort and its source, subagent delivery, notices.claude --version.- The frontmatter of
./.claude/agents/*.mdand~/.claude/agents/*.md(or under$CLAUDE_CONFIG_DIR), only whether each file setseffort:. - The CLAUDE.md files the hook checks (
~/.claude/CLAUDE.mdor$CLAUDE_CONFIG_DIR/CLAUDE.md,./CLAUDE.md,./.claude/CLAUDE.md) for conflicting rules: narration suppression ("hold findings for the final response", "no closing recap"), anti-formatting rules ("no bullets", "no headers"), "ask before every step".
Step 2 · One table, in the user's language
| Row | Value | Note when it matters |
| Plugin | version from --status, Claude Code version | below 2.1.258: say the hook needs a newer Claude Code |
| Rules | rules_source in plain words: "rules file + hook", "hook only", "CLAUDE.md section", "your own rules file (hook silent)", "disabled" | show base_file when there is one |
| Subagents | the subagents line | |
| Mode | mode, and when it says (auto) add the reason: entrypoint sdk-* → unattended, none → interactive | pinned modes: say "pinned in oh-my-fable.json" |
| Effort | effort and effort_source (live = read from this session, exact; saved = modelSettings for this model; settings = top-level effortLevel; env = CLAUDE_CODE_EFFORT_LEVEL; model default = nothing saved, or a top-level effortLevel this model ignores; X → Y by maxEffortLevel = capped) | Opus 5.5 and Sonnet 5.5 default to medium in Claude Code and ignore a top-level effortLevel in user settings; raise per session with /effort high then s. Fable 5.1 and the other models default to high. At xhigh/max the hook adds block N (stop once the checks pass, no self-started review rounds) |
| Subagents' effort | note only: subagents inherit this session's effort unless their agent file sets effort: | show when an agent file from Step 1 has no effort:, with the file names |
| Rules file | rules_file_version vs plugin_rules_version | lower → "run /fable-setup refresh"; higher → "this session runs an older plugin; start a new session, after updating the plugin if needed (no refresh)" |
| CLAUDE.md conflicts | count, then one line per conflict with the file and the suggested replacement | none → "none" |
| Notice | the notice line when it is not (none) |
Then close with exactly one line, translated: "Nothing was changed. /fable-setup changes settings,
/fable <request> improves a single request."
One status line: DONE (or DONE_WITH_CONCERNS when a row needs action).
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.