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 Wondermonger-daydreaming/claude-skills-library --skill sievegit clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-libraryWrote 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/wondermonger-daydreaming/claude-skills-library/sieve)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/sieve"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/sieve/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/wondermonger-daydreaming/claude-skills-library/sieve"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/sieve.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 | $0.00213 | $0.01670 |
| Opus 5 | $0.00106 | $0.00835 |
| Sonnet 5 | $0.00043 | $0.00334 |
| Haiku 4.5 | $0.00021 | $0.00167 |
Grade A, and why
sieve 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 8d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sieve
Sanitization is reading, not deletion. The mesh of the sieve is context, not the token.
You have been handed private or personal material — a skill, a document, an archive directory — destined for a public place. Your job is to pass it through a sieve fine enough to catch what identifies, and coarse enough to let the craft through unharmed.
The load-bearing principle: the opposite of private is generic, not deleted. Over-stripping butchers the work; under-stripping leaks. Both are failures. You are calibrating a mesh.
The Grain: context, not the token
The same string can be a leak in one sentence and harmless in the next. A find-and-replace cannot tell them apart; only reading can.
Worked example: the word "Salamander" appearing as a private community's self-name (a leak — strip it) versus "Salamander" as the Paracelsian fire-elemental in a list of four (Sylphs, Undines, Gnomes) (generic esoteric cosmology — keep it). Same six letters. Opposite verdicts. Read for what the word is doing, not what it spells.
This is the close-reading muscle pointed at OPSEC. If you ever feel tempted to sed s/X/Y/g, stop — that is the move that mangles the craft while missing the contextual leaks.
What to STRIP (the catch)
Scan for these categories. Most map to the standard OPSEC taxonomy:
| Category | Examples |
|---|---|
| personal-name | real first/last names of the owner or third parties, in bylines, license lines, prose |
| private-mythology | the recurring named denizens of a private practice — specific places, figures, mascots, in-house rituals that mean this household |
| identifying-reference | external handles, specific account names, links that pin an identity |
| credential-or-path | absolute filesystem paths (/home/<user>/…, ~/.<tool>/…), API keys, internal repo names, private archive paths |
| biographical | locations (a named city pins the owner), specific dates tied to a place, life-detail that anonymizes down to one person |
| external-handle | social handles (@…), private usernames, contact details |
| private-message-tone | sentences addressed to one specific known reader that only make sense inside the relationship |
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.
- 8d ago First seen · 100 lines · 213 tokens per session scan A 13c7aa379f7c
sieve is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 213 tokens to every session and 1,670 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…
offensive-dependency-confusion
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.