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 agent-ecosystem/agent-skill-implementation --skill probe-bulk-filesgit clone --depth 1 https://github.com/agent-ecosystem/agent-skill-implementationWrote 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/agent-ecosystem/agent-skill-implementation/probe-bulk-files)<a href="https://agentmods.dev/skills/agent-ecosystem/agent-skill-implementation/probe-bulk-files"><img src="https://agentmods.dev/badge/skills/agent-ecosystem/agent-skill-implementation/probe-bulk-files/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/agent-ecosystem/agent-skill-implementation/probe-bulk-files"><img src="https://agentmods.dev/badge/skills/agent-ecosystem/agent-skill-implementation/probe-bulk-files.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 | $0.00036 | $0.00287 |
| Opus 5.5 | $0.00014 | $0.00115 |
| Sonnet 5.5 | $0.00007 | $0.00057 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
probe-bulk-files 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 23d 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 CC-BY-4.0
The repository is licensed CC-BY-4.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
43 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.
- .hidden-dotfile-marker.md 116 B
- assets/binary-pixel-marker.png 70 B
- references/bulk-file-01.md 109 B
- references/bulk-file-02.md 109 B
- references/bulk-file-03.md 109 B
- references/bulk-file-04.md 109 B
- references/bulk-file-05.md 109 B
- references/bulk-file-06.md 109 B
- references/bulk-file-07.md 109 B
- references/bulk-file-08.md 109 B
- references/bulk-file-09.md 109 B
- references/bulk-file-10.md 109 B
- references/bulk-file-11.md 109 B
- references/bulk-file-12.md 109 B
- references/bulk-file-13.md 109 B
- references/bulk-file-14.md 109 B
- references/bulk-file-15.md 109 B
- references/bulk-file-16.md 109 B
- references/bulk-file-17.md 109 B
- references/bulk-file-18.md 109 B
- references/bulk-file-19.md 109 B
- references/bulk-file-20.md 109 B
- references/bulk-file-21.md 109 B
- references/bulk-file-22.md 109 B
- references/bulk-file-23.md 109 B
- references/bulk-file-24.md 109 B
- references/bulk-file-25.md 109 B
- references/bulk-file-26.md 109 B
- references/bulk-file-27.md 109 B
- references/bulk-file-28.md 109 B
- references/bulk-file-29.md 109 B
- references/bulk-file-30.md 109 B
- references/bulk-file-31.md 109 B
- references/bulk-file-32.md 109 B
- references/bulk-file-33.md 109 B
- references/bulk-file-34.md 109 B
- references/bulk-file-35.md 109 B
- references/bulk-file-36.md 109 B
- references/bulk-file-37.md 109 B
- references/bulk-file-38.md 109 B
- references/bulk-file-39.md 109 B
- references/bulk-file-40.md 109 B
- vendor/pkg/deep/vendored-lib-marker.js 144 B runs code
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.
- 23d ago First seen · 33 lines · 36 tokens per session scan A 831eb63dfde9
probe-bulk-files is a skill published in the GitHub repository agent-ecosystem/agent-skill-implementation (6 stars, last pushed 22d ago), licensed CC-BY-4.0. It adds 36 tokens to every session and 287 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
quinn
Verifies specified behavior through appropriate tests and truthful coverage reports.
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
agent-qa-result-triage
Triage failed Agent QA runs with MCP evidence, artifacts, logs, fixed failure categories, confidence, and actionable next steps.
android_ui_verification
Automated end-to-end UI testing and verification on an Android Emulator using ADB.
awt-e2e-testing
AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning DB. Install: npx skills add ksgisang/awt-skill --skill awt -g.