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-model-topology-hazard-review/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-model-topology-hazard-review)<a href="https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-model-topology-hazard-review"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-model-topology-hazard-review/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-model-topology-hazard-review"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-model-topology-hazard-review.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 | $0.00052 | $0.00663 |
| Opus 5 | $0.00026 | $0.00331 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
flowguard-model-topology-hazard-review 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 12d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FlowGuard Model Topology Hazard Review
Purpose
Infer actionable future-use hazards from the actual model topology and usage intent; keep unanchored AI concerns observation-only.
Entrypoint Scope
Route id: model_topology_hazard_review; role: public_owner; native owner: model_topology_hazard_review. This standalone FlowGuard satellite skill owns topology-anchored risk routing, not generic brainstorming.
Local Material Routing
Read references/topology_hazard_protocol.md for TopologyDigest, UsageIntent, business-path identity, anchors, dispositions, and completion rules.
Entrypoint Acceptance Map
Accept a current topology digest, usage intent, and evidence boundary; promote only anchored hazards; block unresolved high-impact paths/loops/side effects; hand model, test, reduction, process, and risk work to typed owners.
Use When
- Use before broad done/release/publish confidence when local green may hide duplicate/conflicting paths, broad terminals, repeatable side effects, compatibility paths, or closure/liveness hazards.
Do Not Use When
- Do not use for generic risk lists, unmodeled systems, or as a replacement for maturation, alignment, Risk Evidence Ledger, or Architecture Reduction; return unclear topology to
flowguard.
Required Workflow
- Record usage, scope, topology, business paths, evidence, and gaps. Portable temporal claims bind the digest to the exact
flowguard.portable_model.v1fingerprint and executable obligations. - Per candidate, name its topology anchor, real-use failure, affected element, confidence effect, and disposition.
- Cross-model event/retry/resource/cache/atomicity/external-confirmation hazards may seed bounded interaction candidates, but must reference a BCL/preflight-resolved property owner or emit
owner_missing; seeds are not executed findings. - Resolve, scope with rationale, or issue typed owner-route handoffs and maintenance obligations.
Hard Gates
- Model-purpose gate: pre-build/change freeze task-specific failure(s)/boundary; bind candidate to 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.
- Unanchored concerns cannot block confidence; anchored hazards need current evidence, owner route, or explicit scoped disposition.
- Keep path conflicts, loop liveness, and compatibility/history visible.
- Only explicit reuse/publication or proven cross-project use
triggers strict
risk_template_libraryclosure. - Portable liveness/fairness requires canonical checker evidence for the same graph; prose/metadata and stale or truncated reports cannot pass.
What ships with it
6 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.
- 12d ago First seen · 44 lines · 52 tokens per session scan A 3d1ef2ece77c
flowguard-model-topology-hazard-review is a skill published in the GitHub repository liuyingxuvka/FlowGuard (2 stars, last pushed 17d ago), licensed MIT. It adds 52 tokens to every session and 663 once invoked, about $0.0003 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
inspector-workbench
Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
sentry-app-setup
Create and configure a Sentry internal integration so the assistant can manage issues, alerts, and releases under its own identity.
observal-advanced
Recovers Observal session ingestion, manages CLI upgrades, downgrades and rollback, and performs explicit local Agent fallback when the server is unavailable. Use when the user asks to reconcile missed sessions, repair CLI version state, or continue locally after a confirmed connection or configuration failure.
regex-expert
Regular expression expert for crafting, debugging, and explaining patterns.
sentry
Sentry error tracking and debugging specialist.