FlowGuard: Skill for Codex

.agents/skills/flowguard-existing-model-preflight/SKILL.md

flowguard-existing-model-preflight is a skill for Codex from liuyingxuvka/FlowGuard. It costs 25 tokens per session (585 once invoked), scanned A, original, MIT.

A pre-check for work on an existing code or data system that looks for models, fields, or commitments already responsible for the requested change.

In plain words
What is it for?
Searching related models, specifications, and documentation; identifying owners and evidence; and choosing the appropriate follow-up route before substantial work.
Why use it?
It helps prevent duplicate ownership and reveals whether the change should reuse, extend, create a child, or introduce something new.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is liuyingxuvka/FlowGuard's own configuration. It tells Codex how to work on FlowGuard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything FlowGuard configures →

Reuse

Borrowing it

Nothing to install: this file belongs to liuyingxuvka/FlowGuard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/liuyingxuvka/FlowGuard/main/.agents/skills/flowguard-existing-model-preflight/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/liuyingxuvka/FlowGuard

Made for: Codex.

Wrote 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.

agentmods badge for flowguard-existing-model-preflight

README.md
[![agentmods](https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-existing-model-preflight/github.svg)](https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-existing-model-preflight)
Your own site
<a href="https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-existing-model-preflight"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-existing-model-preflight/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for flowguard-existing-model-preflight

Your own site · 80×15
<a href="https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-existing-model-preflight"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-existing-model-preflight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00585
Opus 5 $0.00013 $0.00293
Sonnet 5 $0.00005 $0.00117
Haiku 4.5 $0.00003 $0.00059

Measured 10d ago against content hash ac673553cba1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

flowguard-existing-model-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 10d 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.

.agents/skills/flowguard-existing-model-preflight/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FlowGuard Existing Model Preflight

This is a standalone FlowGuard satellite skill for existing-model lookup; it does not replace the downstream owner or the FlowGuard check engine.

Purpose

FlowGuard satellite for existing-model boundaries, ownership, evidence, and duplicate risk.

Entrypoint Scope

It owns lookup, not the downstream route.

Local Material Routing

After admission, read references/existing_model_preflight_protocol.md for lookup and proof.

Entrypoint Acceptance Map

Choose reuse, extend, child, new, or none; block duplicate ownership; select a downstream route.

Use When

  • Use before non-trivial work where existing commitments, fields, or models may own the change.

Do Not Use When

  • Do not replace native validation; skip trivial work; return unclear scope to flowguard.

Required Workflow

  1. Audit the observed head, accepted revision, effective intent, commitments, and behavior plane.
  2. Search affected models/specs/docs; bind owners, evidence, WorkContexts, and same-intent surfaces.
  3. Report exact path-quality fingerprints or typed gaps; reuse only with exact identities and topology.
  4. Preserve unknown, contradictory, unmapped, or scoped facts; return lookup, reuse, and duplicate risk.
  5. Blueprint/qualification consumes owner, disposition, provider/profile, and finding identities. The native model directory is the only DNA source; standalone export is retired.

Hard Gates

  • Only an exact observed instance through the accepted revision and complete CurrentEffectiveIntentView is authoritative; history and path matches are candidates.
  • Model-purpose gate: freeze task-specific failure(s) and claim_boundary; bind native good/bad-per-failure/oracle/current evidence. Reusable types are not fixed-purpose: no mode/fallback; only FlowGuard-declared checks may support completion claims. Require the real FlowGuard check engine and AGENTS.md managed record; forbid fake mini-frameworks or caller-authored currentness.
  • Shared words never promote a wrong-plane hit; WorkContext is read-only. Missing or stale owner/provider/mesh/path-quality identity blocks the claim.
  • Lightweight path quality triggers ModelMaturation, not contraction, deep review, or code-edit authority.
  • Blueprint handoffs never copy native inventories; ArchitectureReduction needs current equivalence/facade or retirement proof.
  • Preflight proves lookup/scope only; ModelMaturation decides understanding and DevelopmentProcessFlow admission.

Read the full file on GitHub · 46 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 46 lines · 25 tokens per session scan A ac673553cba1

Subscribe to this mod's changes

flowguard-existing-model-preflight is a skill published in the GitHub repository liuyingxuvka/FlowGuard (2 stars, last pushed 15d ago), licensed MIT. It adds 25 tokens to every session and 585 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories