Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/miaodx/intuitive-flow/intuitive-refactornpx skills add MiaoDX/intuitive-flow --skill intuitive-refactorgit clone --depth 1 https://github.com/MiaoDX/intuitive-flowWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00185 | $0.01020 |
| Opus 5 | $0.00093 | $0.00510 |
| Sonnet 5 | $0.00037 | $0.00204 |
| Haiku 4.5 | $0.00018 | $0.00102 |
Grade A, and why
intuitive-refactor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intuitive Refactor
Use $intuitive-refactor to make selected cleanup canonical: delete stale
surfaces, merge duplicate concepts, move behavior to the right owner, update
callers/tests/docs, and prove the behavior still holds.
This is a compact runtime router for mutation work. $intuitive-reduce-entropy
owns unknown-target discovery and cleanup candidate ranking; return here only
after the user names a target or selects a candidate packet.
Route
| Need | Read |
|---|---|
| Route selection, scope gate, severity guide, evidence ladder | references/mode-router.md |
| Repeated cleanup, oversized modules, stale surfaces, deletion/owner-move ratchets | references/ratchet-mode.md |
| Long-running ratchet overlay, active capsule, selected-slice loop, or repo-wide maintenance goal | references/ratchet-campaign.md and ../_shared/references/durable-run.md |
| Diff-scoped reuse/quality/efficiency review after implementation | references/changed-code-review.md |
| Full legacy guidance, templates, confidence ladder, command naming, persistent-state examples | references/detailed-guidance.md |
If multiple routes match, load the narrowest reference first and add the next one only when the work crosses that boundary.
Operating Rule
Start from a target and a stop condition, not from "make it cleaner."
- Known seam/module/API/stale surface: gate or execute a bounded refactor slice.
- Unknown repo-wide cleanup or deletion/merge discovery: route to
$intuitive-reduce-entropyfirst. Use its selected-candidate packet as this skill's discovery source. - Repeated cleanup or "keep going": run ratchet route, add the campaign overlay only for long-lived/resumed work, execute only selected clear P1/P2 slices, and park uncertain decisions.
- Periodic whole-repo architecture maintenance: add the campaign overlay's repo-wide maintenance goal loop, alternate fresh reduce-entropy handoffs with execution of every clear queue item, and stop only after saturation deduplicates parked and low-value registries.
- Changed-code cleanup: stay diff-scoped; report findings first and fix only when authorized by the user or approved flow.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 99 lines · 185 tokens per session scan A 7e51b6a805ec
intuitive-refactor is a skill published in the GitHub repository MiaoDX/intuitive-flow (48 stars, last pushed 8d ago), licensed MIT. It adds 185 tokens to every session and 1,020 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
release
Create a new release with version bump, release notes, commit, and tag.
sub-tasks
View and manage SubFrame Sub-Tasks. Use when starting work, completing tasks, checking what's pending, or creating new tasks from conversation.
sub-audit
Run a code review and documentation audit on recent changes. Finds bugs, edge cases, missing docs, and type safety issues.
sub-docs
Sync all SubFrame documentation after feature work. Updates AGENTS.md lists, changelog, PROJECTNOTES decisions, and STRUCTURE.json.
sub-ipc
Regenerate the IPC channel reference documentation from ipcChannels.ts type maps.
onboard
Analyze project intelligence files and bootstrap SubFrame's STRUCTURE.json, PROJECTNOTES.md, and initial sub-tasks from existing codebase context.