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-test-alignment/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-test-alignment)<a href="https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-model-test-alignment"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-model-test-alignment.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 5.1 | $0.00019 | $0.00662 |
| Opus 5 | $0.00010 | $0.00331 |
| Sonnet 5 | $0.00004 | $0.00132 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
flowguard-model-test-alignment 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 8d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FlowGuard Model-Test Alignment
Purpose
Compare obligations, bindings, CodeContract, and tests; never decide path quality.
Entrypoint Scope
A standalone FlowGuard satellite skill; owns model_test_alignment rows; hands large evidence to TestMesh.
Local Material Routing
After admission read references/model_test_alignment_protocol.md; load transition, field, or payload details from references/model_test_transition_protocol.md, references/model_test_field_protocol.md, or references/model_test_payload_protocol.md only when triggered.
Entrypoint Acceptance Map
Compare obligations, contracts, and evidence; route gaps.
Use When
- Use for model-code-test coverage, fields, boundaries, or payloads.
Do Not Use When
- Do not split artifacts or make TestMesh a semantic owner; return undefined obligations to
flowguard.
Required Workflow
- List obligations, owner/path ids, current-intent bindings,
ArtifactPayloadContract, relations, and evidence kinds. - Bind affected semantics/witnesses to one owner, code contract, exact test/native member, oracle, and evidence. Verify identities; never re-rank candidates.
- Convert pre-code rows into obligations, contracts, targets, cases, checker designs, or dispositions. Keep static/executed status separate; pass needs current leaf receipts.
- Trace system properties through runtime transitions. Blueprint consumes independent inventory/bindings both ways; helpers remain internal.
- Paths/symbols prove traceability only. Hand semantic/path gaps to ModelMaturation, large evidence to TestMesh, broad claims to risk.
Hard Gates
- Model-purpose gate: freeze task-specific failure(s) and claim_boundary; bind the 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 real FlowGuard check engine and AGENTS.md managed record; forbid a fake mini-framework. Full confidence requires one owner contract and current same-plane test per obligation.
- One intent cannot align to two primary paths. Opaque, stale, skipped, cross-owner, or normative-as-observed evidence does not count.
- Existing intent resolves only through the exact owner in complete
CurrentEffectiveIntentView; delta/history/word/path matches are not authority. - Ordinary alignment is affected-only; whole-target needs explicit scope. Omitted surfaces, orphan helpers, hidden writers, duplicate bindings, or missing semantics/oracles block.
- Path quality cannot license its own witness. Bind exact model, path-quality, maturation, and admission identities; drift is stale.
- Each row binds semantics, owner code/contract, oracle/checker, exact test/native member, and execution owner. Parent success cannot invent a leaf or relabel receipts.
What ships with it
9 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.
- .skillguard/check-manifest.json 37 KB
- .skillguard/compiled-contract.json 45 KB
- .skillguard/contract-source.json 12 KB
- agents/openai.yaml 1.9 KB
- references/model_test_alignment_protocol.md 12 KB
- references/model_test_field_protocol.md 1.1 KB
- references/model_test_payload_protocol.md 1.1 KB
- references/model_test_transition_protocol.md 1.7 KB
- references/templates/model_test_alignment_prompt_template.md 4.0 KB
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.
- 8d ago First seen · 43 lines · 19 tokens per session scan A 21fe4952ddca
flowguard-model-test-alignment is a skill published in the GitHub repository liuyingxuvka/FlowGuard (2 stars, last pushed 12d ago), licensed MIT. It adds 19 tokens to every session and 662 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
copilotkit-contribute
Use when contributing to the CopilotKit open-source project — forking, cloning, setting up the monorepo, creating branches, running tests, and submitting pull requests against CopilotKit/CopilotKit.
voice-agent-test-harness
Drive a fixed suite of spoken tests against a voice agent ("subject") from a co-located machine ("prober"), measure response latency / clarity / accuracy, diff against baseline, and report to the owner over Telegram.
test-harness
Generates pytest test suites with happy path, edge cases, error conditions, fixture scaffolding, mocks, async patterns. Triggers on: "generate tests", "write tests for", "test this function", "create test suite", "pytest for", "unit tests for", "mock strategy for".
surrogate-verifier
Generates structured test assertions and failure diagnostics for skill packages from a definition and task prompt. Triggers on: "verify this skill", "generate assertions", "surrogate verification", "diagnose skill failure". NOT for code review, use pr-review.
ship-workflow
Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation. Triggers on: "ship it", "release this", "prepare for release", "open a PR", "push and PR", "land this", "/ship-workflow".
Kafka Event-Driven Testing
Test Kafka-based event-driven systems, producer and consumer integration tests with Testcontainers, schema compatibility gates, idempotency and ordering verification, dead-letter handling, and end-to-end event flow assertions.