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 bks-lab/open-bridge --skill bridge-curatorgit clone --depth 1 https://github.com/bks-lab/open-bridgeWrote 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-curator)<a href="https://agentmods.dev/skills/bks-lab/open-bridge/bridge-curator"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/bridge-curator/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-curator"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/bridge-curator.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 | $0.00225 | $0.02446 |
| Opus 5 | $0.00112 | $0.01223 |
| Sonnet 5 | $0.00045 | $0.00489 |
| Haiku 4.5 | $0.00022 | $0.00245 |
Grade A, and why
bridge-curator 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridge Curator
bridge-curator is the periodic background-reflection skill. Once a week
(configurable), it walks the Bridge's own state and asks three orthogonal
questions:
- Is the skill library still coherent? (Library pass)
- Is the proposal queue still actionable? (Queue pass)
- What has the system observed about how this user works lately? (User-pattern pass)
The output of all three phases is always proposals — markdown files
under work/_learning/proposals/ with source.type: curator-suggestion.
The curator never edits Bridge files directly. All accepts happen via
/bridge-learn.
This is the deliberate inversion of the autonomy-maximalist curator
pattern observed in some agentic frameworks (e.g. Hermes Agent's
background-curator-fork). See rules/learning-autonomy.md § Layer B for
the full design rationale.
When to run
- Manual: user says
/bridge-curator, "bridge curator", "curator", etc. - Scheduled: weekly via cron or
/schedule, if configured inbridge-config.yaml.learning.curator.schedule. - Surface in
/briefing: on the configuredauto_surface_in_briefingday (default Sunday),/briefingStream D adds a "curator due / overdue" one-liner. Running the curator itself stays manual unless user opts into auto-run.
Arguments
| Argument | Effect | Default |
|---|---|---|
(none) |
Run all three passes sequentially | — |
--pass library |
Only library consolidation | all |
--pass queue |
Only proposal-queue consolidation | all |
--pass user-patterns |
Only user-pattern synthesis | all |
--dry-run |
Surface findings, do NOT write proposals or user-patterns | false |
--since <date> |
Scan window starts at this date (default: last curator run) | last run |
Three passes
Pass 1 — Library
Full procedure in references/library-pass.md.
Scans skills/, protocols/, rules/, docs/. Detects:
- Sleeping skill — no invocation in
skill-usage.jsonlfor ≥30 days (if Phase-4 telemetry on); else heuristic via skill-name inwork/log.md - Trigger overlap — two or more skills with significantly overlapping trigger phrases in their description fields
- Description-budget buster — a SKILL.md description field that alone exceeds 1536 chars (Skills 2.0 discovery budget)
- Umbrella candidate — three or more skills that share a clear parent workflow and could be one skill with internal modes
- Stale doc — a doc whose
last_updated:is older than the last edit to anything it references - Missing scope frontmatter — a skill or agent file without explicit
scope:(already caught by/bridge-auditCheck 6, but the curator cross-references the audit-history JSON to escalate if recurring)
What ships with it
3 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.
- 8d ago First seen · 239 lines · 225 tokens per session scan A 1b27758fb7de
bridge-curator is a skill published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed yesterday), licensed MIT. It adds 225 tokens to every session and 2,446 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 2026-08-31.
Other skills, from other repositories
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks.
docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4)…
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.