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 cafe3310/public-agent-skills --skill text-watermark-fountaingit clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote 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/cafe3310/public-agent-skills/text-watermark-fountain)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/text-watermark-fountain"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/text-watermark-fountain/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/cafe3310/public-agent-skills/text-watermark-fountain"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/text-watermark-fountain.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 | $0.00048 | $0.00894 |
| Opus 5 | $0.00024 | $0.00447 |
| Sonnet 5 | $0.00010 | $0.00179 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
text-watermark-fountain 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 13d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Text Watermark Fountain (Robust Sync-Frame Version)
This skill enables the Agent to embed a string watermark into a text such that it can be recovered even if the text is partially modified, segments are deleted, or new sentences are inserted. It uses a custom Luby Transform (LT) Fountain Code combined with Sync Frames to map the watermark into a sequence of target lengths.
How it works (Robustness Mechanism)
- Sync Markers: The encoding script periodically inserts a unique length pattern
[19, 4, 19](Sync Marker) followed by a Frame ID. - Self-Synchronization: The decoder searches the entire text for these markers using a sliding window. Even if middle segments are removed, the decoder can resynchronize using the next Sync Marker and know exactly which symbols it is looking at.
- Redundancy: By repeating these frames throughout a long text, the watermark becomes extremely difficult to destroy.
Workflow: Embedding a Watermark
When a user asks to embed a watermark (e.g., "name_1") into a text:
-
Generate Length Sequence:
- Run the encoding script:
python3 scripts/encode.py --mark "name_1" --count [TOTAL_DATA_SYMBOLS] - Note the
Lengthsoutput. It will contain periodic19 4 19 [ID]headers.
- Run the encoding script:
-
Precise Text Fine-tuning (Batch Processing): To ensure 100% accuracy, you MUST use a multi-stage approach:
- Step 2.1: Redundancy & Looping: If the original text is significantly longer than the required length sequence, the script handles the symbol indexing. Just ensure you cover all target lengths.
- Step 2.2: Segmentation: Split the source text into segments using allowed punctuation (
，。！？；：、, . ! ? ; :). - Step 2.3: Batch Delegation: Use a subagent to rewrite segments in batches of 5-10.
- Prompt for Subagent: "Rewrite these segments to match EXACT character lengths: [L1, L2, ...]. Maintain meaning. NO internal punctuation allowed within a segment. Count every character (Chinese, English, digits) as 1."
- Step 2.4: Verification: After each batch, run a Python one-liner to verify:
python3 -c "print([len(s.strip()) for s in [SEG1, SEG2, ...]])"
What ships with it
4 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.
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.
- 13d ago First seen · 64 lines · 48 tokens per session scan A aa46a56fd7e4
text-watermark-fountain is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 894 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
experts
Assemble a panel of experts to assess a problem from multiple professional perspectives, surface agreement and disagreement, and deliver a chaired recommendation with clear tradeoffs. Use when the user wants multi-expert judgment, a second opinion, design critique, option comparison, or a recommendation backed by…
create-plan
A guide for creating repository-aware technical plans: written proposals for implementation, refactoring, migration, or design work based on the actual codebase.
github-release-notes-writer
Draft or update user-focused GitHub Release Notes from verified tags, commits, pull requests, existing releases, and supplied changelog baselines. Use when preparing prerelease or stable release notes, turning GitHub's generated What's Changed list into a curated narrative, documenting upgrades or breaking changes, or…
google-fonts-curator
Recommend high-taste Google Fonts for websites based on brand tone, page type, and visual direction. Use when the user needs font selection, font pairing, or aesthetic judgment within the Google Fonts ecosystem for landing pages, brand sites, editorial pages, portfolios, or digital products.
programmer-motivator
Give calm, technically grounded encouragement to programmers when the user is stuck on a bug, frustrated by debugging, tired, discouraged, blaming themselves after a mistake, asking for motivation or emotional support while coding, wanting someone to stay with them through a hard problem, celebrating a breakthrough…
subagent-orchestrator
Orchestrate subagent workflows for complex tasks that benefit from decomposition, role-based delegation, and parallel execution. Use when Codex should assemble a temporary team of subagents, choose roles from a reusable role library, create a controlled fallback role when no preset role fits, coordinate read-heavy…