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.
curl -O https://raw.githubusercontent.com/liuyingxuvka/FlowGuard/main/.agents/skills/flowguard-architecture-reduction/SKILL.mdgit clone --depth 1 https://github.com/liuyingxuvka/FlowGuardWrote 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/liuyingxuvka/flowguard/flowguard-architecture-reduction)<a href="https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-architecture-reduction"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-architecture-reduction/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.
<a href="https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-architecture-reduction"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-architecture-reduction.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00025 | $0.00686 |
| Opus 5 | $0.00013 | $0.00343 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
flowguard-architecture-reduction 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FlowGuard Architecture Reduction
Purpose
Classify surfaces/steps: retain, contraction, proven retirement, or unresolved.
Entrypoint Scope
A standalone FlowGuard satellite skill; owner architecture_reduction, role public_owner. It proves reductions, not implementation.
Local Material Routing
Read references/architecture_reduction_protocol.md only for an explicit
contraction, retirement, or full audit; routine routing uses this compact
owner contract.
Entrypoint Acceptance Map
Accept DNA, owner/code/test maps, and ModelMaturation provenance; route actions.
Use When
- Use for keep, contraction candidates, retirement, or unresolved review of surfaces and repeated, replaced, or costly steps.
Do Not Use When
- Do not use for greenfield planning, direct refactoring, or unproved behavior change.
Required Workflow
- Ground closure in
CurrentEffectiveIntentView, owners, observed authority, BCL, and blueprint bindings; history/delta are context. Give retained members candidate-independent necessity witnesses; review BCL once. - Whole self/release cleanup uses one current blueprint, one reused reverse-caller index, and one final currentness recheck.
- ModelMaturation owns path judgment. Prove callers, consumers, facade, semantics, tests/oracles, topology, and responsibilities.
- Classify surfaces
retain|contract-equivalent|retire-behavior-with-complete-current-proof|unresolved. Compare normalized semantics, not ids/names; require related surfaces and anObservableArchitectureContractbefore change. - Classify steps as
retain|merge|delegate|remove|explicit_on_demand|unresolved; bind evidence, post-action owner, and required next route.
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.
- Age, membership, tests, cost, or path findings alone prove no decision. Preserve hard semantics before named costs; no scalar/global-optimum claim.
- Retirement disposes every responsibility against complete intent. Keep core DNA under one owner; no alias, compatibility reader/adapter, fallback, forwarder, alternate success path, or second authority.
- Merge/delegate/remove/on-demand requires complete callers, equivalence/replacement proof, post-action owners, and a named on-demand trigger.
- Missing, stale, foreign, ambiguous, or rewrapped evidence blocks. Public/large work needs StructureMesh; implementation needs DevelopmentProcessFlow and affected revalidation.
- Read-only self-audit consumes one current aggregate receipt. Explicit proof freezes a finite batch, reuses current evidence first, and never adds a second registry/store.
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.
- 10d ago First seen · 45 lines · 25 tokens per session scan A a38267442742
flowguard-architecture-reduction 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 686 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.
Other skills, from other repositories
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
repo-audit
Run a comprehensive language-agnostic repository health audit, scored 0-100. Detects language, runs native tooling, never assumes JS/Python.
github
Full GitHub CLI control — issues, PRs, code reviews, repo management. Uses gh CLI with auth detection, rate limiting, and templates. Triggers on: github, issue, pull request, PR, code review, repo, branch, label, assignee, milestone, release, workflow, actions.
security-audit
Security audit expert for OWASP Top 10, CVE analysis, code review, and penetration testing methodology.
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
package-evaluator
Evaluates Claude Code package quality across 6 dimensions for all 7 package types, producing scored audit reports. Triggers on: "evaluate package", "audit agent quality", "score this hook", "package audit", "skill quality check". NOT for LLM prompts, use prompt-lab.