context-advisor

context-advisor is an agent for Claude Code from Sagargupta16/claude-skills. It costs 76 tokens per session (280 once invoked), scanned A, original, MIT.

An agent that evaluates how healthy the current conversation context is and recommends how to manage it.

In plain words
What is it for?
Estimating context usage, checking for context degradation, assessing whether work is in progress, and giving a recommended next action.
Why use it?
Long or messy sessions can cause repeated mistakes, forgotten project instructions, or generic answers. This agent identifies those symptoms and suggests whether to continue, compact, clear, or start a new session.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the context-management plugin — 1 skill, 1 command, 1 agent shipped together

Good fit Estimating context usage, checking for context degradation, assessing whether work is in progress, and giving a recommended next action.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sagargupta16/claude-skills/context-advisor
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.

Clone the repo
git clone --depth 1 https://github.com/Sagargupta16/claude-skills

Made for: Claude Code.

Or install context-management, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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 context-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/sagargupta16/claude-skills/context-advisor.svg)](https://agentmods.dev/agents/sagargupta16/claude-skills/context-advisor)
Your own site
<a href="https://agentmods.dev/agents/sagargupta16/claude-skills/context-advisor"><img src="https://agentmods.dev/badge/agents/sagargupta16/claude-skills/context-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 280 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00076 $0.00280
Opus 5 $0.00038 $0.00140
Sonnet 5 $0.00015 $0.00056
Haiku 4.5 $0.00008 $0.00028

Measured 8d ago against content hash 5489e387971e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

context-advisor 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.

plugins/context-management/agents/context-advisor.md · 34 lines

What it actually says

Context Health Advisor

Process

  1. Estimate context usage based on conversation length and complexity
  2. Look for symptoms of context rot:
    • Repeated mistakes or ignored corrections
    • Generic output that doesn't match project conventions
    • Instructions from CLAUDE.md being forgotten
  3. Assess the current task state:
    • Is work in progress that needs context preserved?
    • Are there failed approaches polluting the context?
    • Is the task nearly complete or just starting?
  4. Recommend the best action with specific reasoning

Output Format

## Context Health Assessment

**Estimated usage**: [low/medium/high/critical]
**Symptoms**: [list any context rot symptoms observed]

**Recommendation**: [Continue / Compact / Clear / New Session]
**Reason**: [why this action]
**Instructions**: [specific steps to take]
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. 8d ago First seen · 34 lines · 76 tokens per session scan A 5489e387971e

Subscribe to this mod's changes

context-advisor is an agent published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 280 once invoked, about $0.0004 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 agents, from other repositories