FlowGuard: Skill for Codex

.agents/skills/flowguard-structure-mesh/SKILL.md

flowguard-structure-mesh is a skill for Codex from liuyingxuvka/FlowGuard. It costs 48 tokens per session (646 once invoked), scanned A, original, MIT.

A procedure for planning and checking the split of a large existing code surface into separately owned parts. It focuses on preserving public entry points, configuration, side effects, dependencies, and compatibility.

In plain words
What is it for?
Dividing large scripts, modules, packages, commands, public APIs, facades, configuration surfaces, or plug-in entry points while checking ownership, dependency cycles, and behaviour parity.
Why use it?
It reduces the risk that a refactor breaks imports, commands, APIs, plug-ins, configuration, or behaviour that users already rely on.

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-structure-mesh/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-structure-mesh

README.md
[![agentmods](https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-structure-mesh/github.svg)](https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-structure-mesh)
Your own site
<a href="https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-structure-mesh"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-structure-mesh/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-structure-mesh

Your own site · 80×15
<a href="https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-structure-mesh"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-structure-mesh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 646 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 $0.00048 $0.00646
Opus 5 $0.00024 $0.00323
Sonnet 5 $0.00010 $0.00129
Haiku 4.5 $0.00005 $0.00065

Measured 9d ago against content hash d3e5ba3679fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

flowguard-structure-mesh 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 9d 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-structure-mesh/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FlowGuard Structure Mesh

Purpose

Govern an existing-code split while preserving public entrypoints, facades, config, effects, cycles, and parity.

Entrypoint Scope

A standalone FlowGuard satellite skill; owns structure_mesh_maintenance (public_owner) evidence, not behavior invention or edits.

Local Material Routing

After admission, read references/structure_mesh_protocol.md for target derivation, partitions, evidence scopes, and handoffs.

Entrypoint Acceptance Map

Accept a named model/surface; derive child ownership; block facade/owner/cycle/config/parity gaps; hand evidence onward.

Use When

  • Use for splitting large code surfaces, moving public imports/CLI/API/data/plugin entrypoints, dividing state/config/side effects, or checking dependency cycles and parity.

Do Not Use When

  • Do not derive behavior requirements from scratch, recommend greenfield modules, refactor code directly, or claim parity from internal/formatting checks; return unclear models to flowguard.

Required Workflow

  1. Accept ArchitectureReduction only with universe member, observable contract, current equivalence/facade proof, consumers/tests, action, and next route; otherwise unresolved. Derive modules from named model maps.
  2. Partition functions, state, config, effects, contracts, dependencies, public entrypoints, and facades to single owners.
  3. For blueprint scope, consume the independent inventory fingerprint and exact required ids; require one owner or terminal disposition per surface.
  4. Attach current routine/release parity and hand gaps/obligations downstream.

Hard Gates

  • Model-purpose gate: freeze task-specific failure(s)/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 real FlowGuard check engine and AGENTS.md managed record; forbid a fake mini-framework.
  • Missing target structure, facade, owner, compatibility, or current parity blocks its scope. StructureMesh does not discover source; stale inventory, omitted surfaces, or fingerprint mismatch blocks blueprint closure.
  • ArchitectureReduction requires a concrete universe member, contract, current proof, target action, and next route; similarity, size, or origin is not proof.
  • Dependency/config and release-only gaps stay visible.
  • Only explicit reuse/publication or proven cross-project use triggers strict risk_template_library closure.
  • Blueprint depth/first gap, explicit whole scope, affected-only default, exact ownership, and separate decision axes follow the protocol.

Read the full file on GitHub · 42 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. 9d ago First seen · 42 lines · 48 tokens per session scan A d3e5ba3679fc

Subscribe to this mod's changes

flowguard-structure-mesh is a skill published in the GitHub repository liuyingxuvka/FlowGuard (2 stars, last pushed 13d ago), licensed MIT. It adds 48 tokens to every session and 646 once invoked, about $0.0002 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.