capability-broker

capability-broker is a skill for Claude Code from bks-lab/open-bridge. It costs 232 tokens per session (2,005 once invoked), scanned A, original, MIT.

A guided process for finding and adding a missing tool or coding skill. It checks whether the gap is real, then asks for confirmation before researching, installing, or creating anything.

In plain words
What is it for?
Use it when an agent cannot perform a requested task, when you want to find a tool, or when you want to create a dedicated skill for a recurring need.
Why use it?
It prevents an agent from assuming a capability is missing or making unapproved changes to the environment.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Install

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.

agentmods
npx agentmods add skills/bks-lab/open-bridge/capability-broker
Any agent
npx skills add bks-lab/open-bridge --skill capability-broker
Clone the repo
git clone --depth 1 https://github.com/bks-lab/open-bridge

Made for: Claude Code.

Wrote 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.

agentmods badge for capability-broker

README.md
[![agentmods](https://agentmods.dev/badge/skills/bks-lab/open-bridge/capability-broker.svg)](https://agentmods.dev/skills/bks-lab/open-bridge/capability-broker)
Your own site
<a href="https://agentmods.dev/skills/bks-lab/open-bridge/capability-broker"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/capability-broker.svg" alt="Measured on agentmods" height="20"></a>
Per session 232 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,005 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00232 $0.02005
Opus 5 $0.00116 $0.01002
Sonnet 5 $0.00046 $0.00401
Haiku 4.5 $0.00023 $0.00200

Measured 6d ago against content hash 8997de219e27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

capability-broker 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 6d 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.

skills/capability-broker/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capability Broker

The acquisition arm of the Bridge learning loop. The other arms look backward and refine what exists (task-close-postmortem, bridge-audit, bridge-curator); this one looks forward and gains a new capability — a tool or a skill — when the user hits something the Bridge can't do yet.

It proposes, it never auto-acts. Every install, every outward step, every persistent write is propose-then-confirm. Same human-gate-at-every-layer posture as rules/learning-autonomy.md — this skill is bound by that rule, not an exception to it.

Read this file only when triggered. Full procedures live in references/ (progressive disclosure) — load the one you need, not all four.

When this skill runs

Entry Mode
The capability-gap-offer standing-order detects a true gap Auto-offer — surface the 4-way offer, then route
User says "the bridge can't do X", "build a skill for this", "is there a tool that…" Direct — same flow, user-initiated
User picks a route from a prior offer (r/s/o/d) Route — jump to the chosen branch

The flow (one screen)

  1. Guard — confirm it's a true gap, not a false one. → references/gap-detection.md
  2. Offer — one question, four routes. Never silently fail or silently one-off.
  3. Route:
    • [r] research + provision a tool → references/research-playbook.md → decision tree
    • [s] scaffold a skill → decision tree → hand to skill-creator
    • [o] one-off → do it now, ledger note only
    • [d] decline → ledger note, cooldown
    • decision tree (provision vs skill vs both) → references/provision-vs-skill.md
  4. Capture — write the learning so it compounds. → references/learning-capture.md

1. Guard — true gap vs false gap

Before offering, run the cheap guard (full steps in references/gap-detection.md). Five outcomes:

  • T1 true gap — no skill, no wired tool, not native → offer (step 2).
  • T2 dormant skill — a skill plausibly covers it but didn't fire → load it; if it mis-triggered, log a trigger-correction (existing loop). Stop — not this skill's job.
  • T3 native — Claude can already do it with built-in tools → just do it.
  • T4 one-off — real but single-use → do it ad-hoc, ledger note.
  • T5 declined/policy — declined this session or must-not-do → silent / refuse.

Read the full file on GitHub · 163 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 163 lines · 232 tokens per session scan A 8997de219e27

Subscribe to this mod's changes

capability-broker is a skill published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed today), licensed MIT. It adds 232 tokens to every session and 2,005 once invoked, about $0.0012 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.

Related

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…

AminulIslamSifat/Sable · 96 tokens

pdf

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.

AminulIslamSifat/Sable · 50 tokens

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.

AminulIslamSifat/Sable · 62 tokens

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)…

AminulIslamSifat/Sable · 77 tokens

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.

a5c-ai/babysitter · 44 tokens

quality-hooks

Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.

a5c-ai/babysitter · 53 tokens