Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bks-lab/open-bridgenpx agentmods add skills/bks-lab/open-bridge/bridge-explorerWrote 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/bks-lab/open-bridge/bridge-explorer)<a href="https://agentmods.dev/skills/bks-lab/open-bridge/bridge-explorer"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/bridge-explorer/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/bks-lab/open-bridge/bridge-explorer"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/bridge-explorer.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 | $0.00063 | $0.00605 |
| Opus 5.5 | $0.00025 | $0.00242 |
| Sonnet 5.5 | $0.00013 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
bridge-explorer 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 1mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridge Explorer
Visualize Bridge state as interactive HTML dashboards. Read the referenced file ONLY when triggered.
Decision Tree
User wants to...
├── Ecosystem visualization → Read references/workflow.md
├── CORE/USER repo split visual → Read references/repo-layout.md
│ (triggers: "repo layout", "core/user", "where do files live",
│ "repo structure"; pick variant v1–v4 or c-prime, see below)
├── Information flow / network → Render + open the network variant
│ (triggers: "network diagram", "constellation", "how is everything linked",
│ "how does the bridge distribute information", "layers")
└── Questions about ecosystem → Read ecosystem.yaml directly
Repo-layout variants
All variants render the same CORE/USER + cluster-wrapper split, sourced from
docs/repo-layout/regions.yaml (single source of truth — edit there, all
variants pick up on regenerate).
Constellation (network) is generated, not hand-edited. Its nodes/edges/flows
live in regions.yaml under constellation: (schema v3). After editing them run:
python3 docs/repo-layout/build-constellation.py
This injects the JS data block into network.html between the CONSTELLATION-DATA
markers and bumps the version badge. Precondition: network.html must have been
rendered first — the script refreshes the data block of an existing rendered file;
on a fresh clone there is no network.html yet, so render it via this skill first.
Wire it into your deploy pipeline so the served HTML never drifts from
regions.yaml by hand.
| Variant | Lens |
|---|---|
| c-prime | Editorial cluster/top-level map (primary, dense) |
| network | Constellation — 5-ring information network (hub → brain → synapses → memory → state → world), 4 sectors (Meta · Operations · CustomerA · Identity), bundled edges, named flows |
| v1 | Hemispheric brain (CORE left, USER right) — static SVG |
| v2 | Brain with anatomical region labels + side panel |
| v3 | Interactive brain — click region for drill-down |
| v4 | Minimal two-column schematic — dense, print-friendly |
What ships with it
2 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.
- 1mo ago Changed · -5 lines · -68 tokens per session 02f261edcea7
- 2mo ago First seen · 67 lines · 131 tokens per session scan A 6309edc5ffd4
bridge-explorer is a skill published in the GitHub repository bks-lab/open-bridge (13 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 605 once invoked, about $0.0003 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 2026-08-31.
bridge-explorer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bridge-explorerbks-lab/open-bridge | Skill | 13 | yesterday | MIT | A | 63 | Claude Code, Codex |
| wireframepaperclipai/paperclip | Skill | 112k | today | MIT | A | 47 | Claude Code, Codex |
| design-critiquepaperclipai/paperclip | Skill | 112k | today | MIT | A | 42 | Claude Code, Codex |
| paperclip-capsulespaperclipai/paperclip | Skill | 112k | today | MIT | A | 41 | Claude Code, Codex |
| mcp-host-styling-integrationa5c-ai/babysitter | Skill | 1.9k | 5d ago | MIT | A | 44 | Claude Code |
| tutti-ui-systemtutti-os/tutti | Skill | 3.9k | 1mo ago | Apache-2.0 | A | 46 | Claude Code, Codex |
| ux-designa5c-ai/babysitter | Skill | 1.9k | 5d ago | MIT | A | 0 | Claude Code, Codex |