insane-search
Impossible is nothing. If it's public, insane-search gets in. A resilient public-page reader for Claude Code. No API keys, no proxy setup. insane-search breaks through and returns real public content with its source. -->
A Claude Code plugin that makes Opus (or any Claude model) see a task through to the end — with evidence and verification — as procedure, not as luck.
> /plugin marketplace add fivetaku/fablize> /plugin install fablize@fablize
What's inside
English | 한국어
A Claude Code plugin that makes Opus (or any Claude model) see a task through to the end — with evidence and verification — as procedure, not as luck.
When Fable 5 shipped, I ran a controlled comparison of Fable 5 and Opus 4.8 (an A/B set of 19 runs plus 26 real working sessions, ~1,500 tool calls). The finding:
fablize applies only the procedures whose effect was verified. It does not raise the model's ceiling; it makes the model reach its own ceiling.
| Trait | Transferable? | Reason |
|---|---|---|
| Verification grounding (run & observe the artifact) | ✅ shipped | A procedure Opus skipped "not because it can't, but because it didn't." Injecting it raised render-verification behavior measurably. |
| Multi-story completion + evidence gate | ✅ shipped | A procedure — decompose, checkpoint, refuse completion without proof. |
| Systematic investigation (reproduce → hypotheses → causal chain) | ✅ shipped | A procedure — on par with what the strong model already does. |
| Early-stop prevention | ✅ shipped | A deterministic hook — catches "I'll do X" without doing it. |
| Out-of-spec defect discovery | ❌ not possible | Capability. Injection was refuted — the model finds it, or it doesn't. |
| Open-ended creative detail | ❌ not possible | Capability. Shows only where there is no fixed answer. |
| Self-driven propagation depth | ❌ not possible | Capability. Directed propagation transfers; self-started depth does not. |
The non-transferable rows are the model's job (or a human's), not a harness's. When you hit them, fablize tells you to escalate instead of pretending.
goals.py decomposes work and refuses a groundless "done."Negligible or unverified ideas (style mimicry, broad reasoning injection, a silent-recovery guard, a review-recall scan) are not shipped. They stay in personal development until a controlled experiment confirms their effect.
/plugin marketplace add fivetaku/fablize
/plugin install fablize
The per-task router (a UserPromptSubmit hook) registers automatically.
For always-on operation (the rules resident in context), run once:
bash ${CLAUDE_PLUGIN_ROOT}/setup/setup.sh # choose local (recommended) or global
Uninstall: bash ${CLAUDE_PLUGIN_ROOT}/setup/uninstall.sh
If fablize helps, a ⭐ on the repo means a lot — setup asks once (a single opt-in question); it never stars without your explicit "yes".
/fablize or phrases like "see it through", or automatically when installed always-on./effort xhigh suggestion.MIT — see LICENSE.
Impossible is nothing. If it's public, insane-search gets in. A resilient public-page reader for Claude Code. No API keys, no proxy setup. insane-search breaks through and returns real public content with its source. -->
FAQ
fablize is a Claude Code plugin with 1 hand-picked skill for agent orchestration work, indexed on Flowy. Install it with the command on its page. It includes fablize. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it