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-preflightnpx skills add MiaoDX/intuitive-flow --skill intuitive-preflightgit clone --depth 1 https://github.com/MiaoDX/intuitive-flowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/miaodx/intuitive-flow/intuitive-preflight)<a href="https://agentmods.dev/skills/miaodx/intuitive-flow/intuitive-preflight"><img src="https://agentmods.dev/badge/skills/miaodx/intuitive-flow/intuitive-preflight.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00112 | $0.02074 |
| Opus 5 | $0.00056 | $0.01037 |
| Sonnet 5 | $0.00022 | $0.00415 |
| Haiku 4.5 | $0.00011 | $0.00207 |
Grade A, and why
intuitive-preflight 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 4d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intuitive Preflight
Use this skill to make execution intent explicit before work starts. The output is a preflight contract the user can approve, revise, or reject. It is not an implementation step.
Preflight should make the smallest honest contract approvable. Before allowing new files, APIs, modules, commands, workers, plans, tests, docs, compatibility bridges, or persistent workflow surfaces into scope, first test whether the same observable outcome can be achieved by deleting, merging, narrowing, reusing, or documenting existing behavior. Record any necessary new entity with its reason and re-approval trigger.
When the user gives an existing plan file as the task source, "smallest honest"
means the smallest honest contract for executing that plan, not the smallest
slice inside it. Preserve the plan's full intended scope by default and encode
risky pieces as ordering, stop gates, local/live validation gates, or
BLOCKED_NEEDS_DECISION conditions. Narrow the preflight to a subset only when
the user asks for partial execution, the plan is broader than the user's stated
goal, or full-plan execution would be dishonest without another decision.
Boundary
$intuitive-preflight owns scope, non-goals, acceptance criteria, context
packaging, route choice, /goal execute ... with intuitive-flow wording, worker
scope, and missing user-owned decisions. It does not execute, create or clear
/goal, launch skill-runner, edit product files, or approve itself.
After approval, execution normally returns to $intuitive-flow. For known
refactor or cleanup preflight contracts, execution may route to
$intuitive-refactor.
When To Stop And Ask
Stop with BLOCKED_NEEDS_DECISION instead of drafting a fake-complete contract
when any of these are unclear and materially change the work:
- target user, product intent, or desired behavior
- public contract, API, or data model
- scope/non-goal boundary
- required context source, artifact, file, issue, plan, or log
- acceptance criteria or success threshold
- destructive action or broad file movement
- user-explicit temporary compatibility or migration bridge requirement
- paid, credentialed, hardware, Docker, GPU, real simulator, or provider gate
- any new durable entity whose necessity is unclear or whose addition would expand the accepted objective
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.
- 4d ago First seen · 198 lines · 112 tokens per session scan A 5a84d2155179
intuitive-preflight is a skill published in the GitHub repository MiaoDX/intuitive-flow (48 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 2,074 once invoked, about $0.0006 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
neo4j-graphql-skill
Build and configure a GraphQL API backed by Neo4j using @neo4j/graphql v7 (current) or v5 (LTS). Covers Neo4jGraphQL constructor, getSchema(), assertIndexesAndConstraints(), type definitions with @node, @relationship (IN/OUT/UNDIRECTED), @cypher for custom resolvers, @authorization/@authentication for JWT/JWKS…
fpf-problem-solving
Use First Principles Framework (FPF) to solve problems, architect systems, evaluate alternatives, decompose complexity, classify problems, define quality, recover methods from work evidence, steer or recovery-test work, screen mandatory workflow steps, discover consequence-bearing systems, compare configuration…
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.