Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tianqi-era-ai/Longwang-Claw --skill loop9-verify-v4git clone --depth 1 https://github.com/tianqi-era-ai/Longwang-ClawWrote 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/tianqi-era-ai/longwang-claw/loop9-verify-v4)<a href="https://agentmods.dev/skills/tianqi-era-ai/longwang-claw/loop9-verify-v4"><img src="https://agentmods.dev/badge/skills/tianqi-era-ai/longwang-claw/loop9-verify-v4/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/tianqi-era-ai/longwang-claw/loop9-verify-v4"><img src="https://agentmods.dev/badge/skills/tianqi-era-ai/longwang-claw/loop9-verify-v4.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 | $0.00078 | $0.06129 |
| Opus 5 | $0.00039 | $0.03064 |
| Sonnet 5 | $0.00016 | $0.01226 |
| Haiku 4.5 | $0.00008 | $0.00613 |
Grade A, and why
loop9-verify-v4 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.
The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
33 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.
- references/agentic-blocker-diagnosis.md 5.6 KB
- references/board-closure-verdict.md 3.9 KB
- references/canonical-objects.md 9.5 KB
- references/child-return-consume-seam.md 3.4 KB
- references/current-status.md 9.5 KB
- references/experience-index.md 14 KB
- references/experience-sedimentation.md 9.0 KB
- references/first-wave-child-skills.md 1.6 KB
- references/handoff-compiler.md 4.4 KB
- references/learning-delta.LDV4-003.delivery-report-stage-barrier.md 2.2 KB
- references/learning-delta.LDV4-004.runtime-materialization-vs-transport-failure.md 2.5 KB
- references/learning-delta.LDV4-005.state-changing-poc-needs-landing-proof.md 2.3 KB
- references/learning-delta.LDV4-007.shared-blocker-repair-before-row-freeze.md 2.8 KB
- references/learning-delta.LDV4-008.action-probe-vs-canonical-replay.md 3.3 KB
- references/learning-delta.LDV4-009.auth-accessory-break-vs-finding-blocker.md 3.2 KB
- references/learning-delta.LDV4-010.active-inflight-anchor-vs-detached-continuation.md 3.1 KB
- references/owner-placement-matrix.md 5.9 KB
- references/parent-boundary.md 6.1 KB
- references/parent-closure-chain.md 3.9 KB
- references/parent-io-contract.md 13 KB
- references/parent-minimal-core.md 3.0 KB
- references/proof-gap-sample-selection.md 2.2 KB
- references/recurring-recovery.md 4.8 KB
- references/repo-execution-core.md 7.0 KB
- references/repo-queue-workflow.md 4.3 KB
- references/repo-selection-pack.md 6.3 KB
- references/repo-selection.md 10 KB
- references/repo-start-pack.md 7.6 KB
- references/repo-task-brief.md 4.3 KB
- references/round-storage.md 4.5 KB
- references/runtime-isolation.md 11 KB
- references/runtime-target.tencent-cvm.md 5.1 KB
- references/stage-chain.md 7.6 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.
- 11d ago First seen · 476 lines · 78 tokens per session scan A 7f6aa36d8e81
loop9-verify-v4 is a skill published in the GitHub repository tianqi-era-ai/Longwang-Claw (5 stars, last pushed 4mo ago), licensed GPL-3.0. It adds 78 tokens to every session and 6,129 once invoked, about $0.0004 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
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.
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.