What is booster-context?

A coding-agent skill that uses Agent Booster tools to find code, read only relevant parts of files, inspect file structure, and choose a model tier. It can also run a background index that updates when files change.

Use it to search symbols, inspect focused code sections, keep an index current, manage the Agent Booster daemon, and route tasks to different model tiers.

It reduces the amount of code an agent needs to read and helps searches return quickly in indexed projects.

booster-context — Skill for Claude Code by sseshachala: A coding-agent skill that uses Agent Booster tools to…

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/sseshachala/agent-booster/booster-context

Any agent

npx skills add sseshachala/agent-booster --skill booster-context

Clone the repo

git clone --depth 1 https://github.com/sseshachala/agent-booster

Made for: Claude Code.

Or install agent-booster, the plugin that ships this one along with the rest of its 1 skill, 4 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sseshachala/agent-booster/booster-context.svg)](https://agentmods.dev/skills/sseshachala/agent-booster/booster-context)

Your own site

<a href="https://agentmods.dev/skills/sseshachala/agent-booster/booster-context"><img src="https://agentmods.dev/badge/skills/sseshachala/agent-booster/booster-context.svg" alt="Measured on agentmods" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 394 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.00394
Opus 5	$0.00025	$0.00197
Sonnet 5	$0.00010	$0.00079
Haiku 4.5	$0.00005	$0.00039

Measured 5d ago against content hash 5261b590ed7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

booster-context 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 5d 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.

Origin

This is a copy

100% identical to booster-context — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude-plugin/skills/booster-context/SKILL.md · 46 lines

What it actually says

When to use

Prefer Agent Booster tools over native Read/Grep whenever the project has been indexed:

mcp__agent-booster__search_context — semantic search across all symbols (replaces Grep)
mcp__agent-booster__smart_read — returns only the relevant slice of a file for a task (replaces Read)
mcp__agent-booster__get_symbols — survey a file's structure before reading
mcp__agent-booster__route_model — pick the right model tier (haiku/sonnet/opus) based on task complexity

Setup

pip install 'agent-booster[full]'   # includes embeddings + file watcher
booster init claude                  # wire MCP, hooks, CLAUDE.md
booster start                        # background daemon — model warm + file watcher

Daemon commands

booster start     # start daemon in background
booster stop      # stop daemon
booster status    # show pid, uptime, watcher state

With the daemon running:

search_context responds in ~50ms instead of 2-3s (no model cold-start)
File changes are automatically re-indexed within 2s (no manual booster index)

Indexing

booster index           # incremental — only re-indexes changed files
booster index --force   # full re-index of everything
booster embed           # rebuild embeddings after manual index

Gains

Run booster gain to see token savings statistics for the current session.

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.

5d ago First seen · 46 lines · 50 tokens per session scan A 5261b590ed7a

Subscribe to this mod's changes

booster-context is a skill published in the GitHub repository sseshachala/agent-booster (1 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 394 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to booster-context, differing in 0 lines, and is treated as a copy.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

booster-context