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 alex-durango/pingfusi --skill pingfusi-reviewgit clone --depth 1 https://github.com/alex-durango/pingfusiWrote 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/alex-durango/pingfusi/pingfusi-review)<a href="https://agentmods.dev/skills/alex-durango/pingfusi/pingfusi-review"><img src="https://agentmods.dev/badge/skills/alex-durango/pingfusi/pingfusi-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/alex-durango/pingfusi/pingfusi-review"><img src="https://agentmods.dev/badge/skills/alex-durango/pingfusi/pingfusi-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01071 |
| Opus 5 | $0.00000 | $0.00535 |
| Sonnet 5 | $0.00000 | $0.00214 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
pingfusi-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 today.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route human judgment through Pingfusi
Use Pingfusi as the real-human verification layer inside an agent's normal work. Ask a reviewer only for the part that requires perception, judgment, a real device, or external reach. Keep deterministic verification in code, tests, documentation or search, and the local browser.
Game playtesting belongs to Qaping. Use npx @qaping/cli setup and
qaping_playtest for games. Pingfusi does not create game playtests or spend
Qaping credits. Existing reports remain accessible.
Choose the job
Use the smallest job whose reviewer can actually see the subject:
| Need | Use |
|---|---|
| One subjective answer, fully expressible in text, with nothing to look at | MCP pingfusi_quick_question, or shell pingfusi ask |
| Verdict and pinned feedback on a website, build, document, or other artifact the reviewer must see — publish it first | MCP pingfusi_review_website |
| Clone compared side by side with its original (the reviewer opens both) | Managed clone CLI when present; otherwise MCP pingfusi_compare_clone |
| Rendered video judged against its current brief and prompt history (the reviewer watches the MP4) | MCP pingfusi_review_video |
A quick question is advisory. Never use it to declare work finished. Work that needs a real DONE/NOT-DONE decision requires a review round with an explicit verdict.
A quick question is also blind: the reviewer receives only the question text and options — no URL opens, no image renders, and a pasted link is dead text on their device. The moment there is anything to look at (a page, build, design, or draft), publish it and file a review round instead, however small or subjective the question. A reviewer cannot act on a question about something they cannot see.
Use one reviewer by default. Increase the reviewer count only when the user asks for broader confidence or the decision's risk clearly justifies the extra cost.
Respect specialized workflows
When targets/<name>/workflow.json exists, run pingfusi next <name> and follow the
managed clone workflow. Do not call raw review MCP tools for that target because they
bypass its gates. Use the specialized installed skills for pixel-perfect cloning,
repairing an existing clone, beautifying a website, and reviewing a video whenever one
of those explicit jobs applies.
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.
- today Changed · +4 lines 784168f7b25d
- 10d ago First seen · 73 lines · 0 tokens per session scan A fc4b829a69cf
pingfusi-review is a skill published in the GitHub repository alex-durango/pingfusi (111 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,071 tokens. 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 2026-08-30.
Other skills, from other repositories
agentplane-task-closure-recovery
Use when Agentplane task completion, direct finish, branchpr integration, hosted-close, close-tail PRs, PR metadata, dirty task artifacts, or remote branch divergence need diagnosis or recovery.
xnaut-review
Leave inline review notes on a worktree's diff inside a running xNaut window. Steers the user's diff viewer; never opens its own.
quaere-audit
This skill should be used whenever the user asks for a serious security audit, vulnerability review, bug bounty triage, threat-model-driven code review, protocol/spec conformance audit, auth/authz or tenant-isolation review, exploitability analysis, CVE/advisory impact assessment, or security-sensitive PR review when…
quaere-evidence
This skill should be used whenever the user asks to investigate unclear bugs, defend or reject PR review comments, triage CI failures or flaky tests, review risky/security/database/concurrency/external-API changes or multi-file refactors, or make any claim that needs evidence before patching. It enforces a falsifiable…
cvg-code-review
Review implementation against the plan and contract. Distinguish code bugs from contract gaps. Bounded convergence.
cvg-build-loop
Orchestrate a monitored implementation loop where a worker implements the plan and fresh code reviewers gate the exit. Use when the user asks to run a supervised implementation or build loop on Codex threads or Claude Code background agents.