Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. 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/greenmtnsun/GitEasy/main/.claude/skills/security-sibling-sweep/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote 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/greenmtnsun/giteasy/security-sibling-sweep)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/security-sibling-sweep"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/security-sibling-sweep/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/greenmtnsun/giteasy/security-sibling-sweep"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/security-sibling-sweep.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 | $0.00192 | $0.02245 |
| Opus 5.5 | $0.00077 | $0.00898 |
| Sonnet 5.5 | $0.00038 | $0.00449 |
| Haiku 4.5 | $0.00019 | $0.00225 |
Grade A, and why
security-sibling-sweep 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See also:
virtual-security-reviewerfor the adversarial-review framing,verify-claims-on-diskfor trust-but-verify on apply claims.
Security Sibling-Sweep
When a security review finds a regex-based parse bug (URL, host, path, credential, env-var) in one location, before declaring the finding closed, fan out across the codebase for sibling expressions of the same root cause. CWE-200/22/78/532-class root causes almost never live in exactly one file.
Skipping the sweep gives a fix that looks complete and leaves a recurrence-prone surface. Real cost when skipped: GitEasy 1.5.1 had to be effectively retired (not published to PSGallery) and a 1.5.2 cut for F-04/F-05/F-06 — three sibling findings the original F-01/F-02/F-03 pass missed.
When this skill activates
Any of:
- A virtual-security-reviewer turn just identified a regex-based parse finding (
^https://(?<Host>[^/]+)/,[^/]+@,.*\.git/config, or similar). - The proposed fix is "replace pattern X with
[uri]parse" / "use[System.IO.Path]::GetFullPath" / "useConvertFrom-StringDatawith bounded keys" / any structured-parser-for-regex swap. - The conversation contains "the finding is closed" / "F-NN is fixed" / "only affects function Y" / "this is the only place that does X" — before that claim is built upon.
- A PR / release tag is about to be cut and a security review was part of the pre-flight.
The four-step protocol
Before any "finding closed" claim, all four steps must run and return either zero hits OR hits already covered by the proposed fix.
Step 1 — Sweep for the pattern shape itself
Grep the whole repo (and ideally the whole Module Suite) for the regex pattern that produced the bug, or its key fragments. Examples:
# If the F-02 fix replaced ^https://(?<Host>[^/]+)/ — sweep for the shape, not just the literal:
Grep -pattern '\^https://\(\?<' -type ps1
Grep -pattern '\[\^/\]\+' -type ps1
Grep -pattern '\[\^@\]\+@' -type ps1 # SSH-style sibling
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 First seen · 117 lines · 192 tokens per session scan A 0548d391e15e
security-sibling-sweep is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 192 tokens to every session and 2,245 once invoked, about $0.0008 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 2026-11-18.
security-sibling-sweep compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| security-sibling-sweepgreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 192 | Claude Code |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 101k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |