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 agentmods add instructions/delorenj/ssbnk/agents-mdgit clone --depth 1 https://github.com/delorenj/ssbnkWrote 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/instructions/delorenj/ssbnk/agents-md)<a href="https://agentmods.dev/instructions/delorenj/ssbnk/agents-md"><img src="https://agentmods.dev/badge/instructions/delorenj/ssbnk/agents-md.svg" alt="Measured on agentmods" 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 | $0.01325 | $0.01325 |
| Opus 5 | $0.00662 | $0.00662 |
| Sonnet 5 | $0.00265 | $0.00265 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
ssbnk AGENTS.md 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ScreenShot Bank (ssbnk)
Project Overview
ssbnk is a self-hosted screenshot/screencast hosting service. It watches local folders, normalizes filenames, hosts assets, and exposes "latest" retrieval endpoints. Remote machines upload screenshots via the /upload API, and the URL is copied to the host clipboard automatically.
Core stack:
- Watcher/API: Go (
/watcher) — serves everything: assets, API, and the built UI - Management UI: Astro + React (
/ui) — static build served by the watcher - Static hosting: Nginx (
/web) — LEGACY, only in the packaged all-in-one image - Remote uploaders: Bash scripts on remote machines (
/scripts)
Full generated docs live in docs/ (start at docs/index.md).
Core Components
1) Watcher (/watcher)
- Watches screenshot and screencast directories via fsnotify.
- Converts videos to GIF (
ffmpeg) and stores metadata JSON inwatcher-data/metadata/. - Copies URL to host clipboard on both local screenshots and remote uploads.
- Writes last screenshot filename to
/tmp/ssbnk/last-screenshotfor paste-image support. - Endpoints (all served by the watcher on
SSBNK_API_PORT, default 80):/api/screenshotspaginated JSON listing for the UI (limit/offset)/latestmetadata-driven lookup (302 redirect)/hybridmetadata + filesystem fallback/statelessfilesystem-only lookup/uploadremote upload endpoint (requiresX-Upload-Keyheader)/healthmetadata/file consistency status- Hosted assets served root-level (
/<file>.png), unknown paths fall through to the UI'sindex.html
2) Management UI (/ui)
- Astro 6 + React 19 + TypeScript + Tailwind 4 + shadcn (on @base-ui/react).
- Static build (
npm run build→dist/); the watcher serves it fromSSBNK_UI_DIR(default/ui). No separate UI server. - Single screen:
ScreenshotGallery.tsxcallingGET /api/screenshots.ui/has its own.git(nested repo).
3) Web Server (/web) — LEGACY
- Nginx configs from the retired 3-container architecture; only used inside the packaged all-in-one image (root
Dockerfile, supervisord). - Proxies only
/uploadand/latestto the watcher on port 31243. The currentcompose.ymlstack has no Nginx container. web/html/holds the live hosted assets.
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 · 80 lines · 1,325 tokens per session scan A 6fe1aa2bd72e
ssbnk AGENTS.md is an instructions file published in the GitHub repository delorenj/ssbnk (2 stars, last pushed today), licensed MIT. It adds 1,325 tokens to every session, about $0.0066 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 instructions, from other repositories
RustifyMyClaw CLAUDE.md
Instructions for Escoto/RustifyMyClaw, covering claude.md — rustifymyclaw, project, module layout, build & run and code rules.
RustifyMyClaw AGENTS.md
Instructions for Escoto/RustifyMyClaw: All project instructions, coding rules, and architecture reference live in CLAUDE.md.
zen-slug-cleaner GEMINI.md
Gemini CLI instructions for wasabina67/zen-slug-cleaner, a project described as: Zen Slug Cleaner 😎.
agentgram CLAUDE.md
Claude Code instructions for agentgram/agentgram, covering claude.md — agentgram development guide, project overview, tech stack, monorepo structure and core architecture patterns.
hqbase AGENTS.md
AGENTS.md instructions for HQBase/hqbase, covering hqbase workspace guide, boundaries and quality gate.
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.