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-miss-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-miss-review)<a href="https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-model-miss-review"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-model-miss-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-miss-review"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-model-miss-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 | $0.00026 | $0.00637 |
| Opus 5 | $0.00013 | $0.00318 |
| Sonnet 5 | $0.00005 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
flowguard-model-miss-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 11d 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 Miss Review
Purpose
Apply root-cause backpropagation from a post-green failure into its commitment, blueprint gap, finite cases, owner code/tests, and claim.
Entrypoint Scope
This standalone FlowGuard satellite skill owns grounded model_miss_review classification and closure, not feature invention.
Local Material Routing
After admission, read references/model_miss_protocol.md for the full protocol.
Entrypoint Acceptance Map
Accept concrete failure evidence and prior claim state; block point-fix-only or stale closure.
Use When
- Use after a FlowGuard-green runtime, test, replay, log, manual, or UI failure, including
boundary_missing.
Do Not Use When
- Do not invent a commitment or proceed without concrete failure evidence; return unclear modeling to
flowguard.
Required Workflow
- Run Existing Model Preflight; bind one commitment, primary owner, complete current-effective-intent owner binding, blueprint gap, error signature, and miss type. If nothing covers the promise, record one coverage gap.
- Backpropagate only the supported cause. A requested diagnostic is a read-only deletion-minimal conflict plus positive witness and preserves the owner decision.
- Declare finite relations from current DNA/BCL/topology identities and pass exact relation/gap ids to ContractExhaustionMesh; no unbounded sibling search or second relation authority.
- Materialize each contract-exhaustion same-class case, combination, or receipt with an oracle; emit one task-bound ModelMaturation contribution.
- Bind cases to the owner code contract and tests. Rerun alignment, affected topology/parent replay, freshness, and maturation risk; close or scope the class.
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 the real FlowGuard check engine and AGENTS.md managed record; forbid a fake mini-framework.
- A later green command or point regression cannot close the class; require target-aware replay and owner-code binding.
- Current intent comes only from the accepted complete
CurrentEffectiveIntentView; never infer repaired DNA from delta, history, root intent, or code path. - Unknown old-path disposition, unresolved canonical case, missing owner-code/test binding, stale parent/topology replay, or open ModelMaturation gap blocks broad confidence.
- Shared symptom text never merges behavior planes. Diagnostics need necessity and positive witnesses; say deletion-/subset-minimal, never global-minimum or unique.
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.
- 11d ago First seen · 43 lines · 26 tokens per session scan A dd9761c11455
flowguard-model-miss-review is a skill published in the GitHub repository liuyingxuvka/FlowGuard (2 stars, last pushed 16d ago), licensed MIT. It adds 26 tokens to every session and 637 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
Playwright (Automation + MCP + Scraper)
Browser automation via Playwright MCP. Navigate websites, click elements, fill forms, take screenshots, extract data, and debug real browser workflows. Use when (1) you need a real browser, not static fetch; (2) the task involves Playwright MCP, browser tools, Playwright tests, scripts, or JS-rendered pages; (3) the…
Bug Fixing
Skill "Bug Fixing" from OpenLabor/openlabor, covering bug fixing, objective, process and guidelines.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.