suggest-split

suggest-split is a skill for Claude Code from msiShariful/claude-token-inspector. It costs 48 tokens per session (747 once invoked), scanned A, original, MIT.

A conversation review that detects when one chat has drifted into several unrelated topics. It identifies the best point to start a new conversation and summarizes the useful context to carry over.

In plain words
What is it for?
Use it to map the topics in a conversation, decide whether to split it, find the split point, and prepare a short handoff summary.
Why use it?
Long, mixed-topic chats can make it harder to find relevant details and give reliable answers. This helps separate unrelated work while preserving important decisions and context.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

Part of the token-inspector plugin — 8 skills shipped together

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/msishariful/claude-token-inspector/suggest-split
Any agent
npx skills add msiShariful/claude-token-inspector --skill suggest-split
Clone the repo
git clone --depth 1 https://github.com/msiShariful/claude-token-inspector

Made for: Claude Code.

Or install token-inspector, the plugin that ships this one along with the rest of its 8 skills.

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 suggest-split

README.md
[![agentmods](https://agentmods.dev/badge/skills/msishariful/claude-token-inspector/suggest-split.svg)](https://agentmods.dev/skills/msishariful/claude-token-inspector/suggest-split)
Your own site
<a href="https://agentmods.dev/skills/msishariful/claude-token-inspector/suggest-split"><img src="https://agentmods.dev/badge/skills/msishariful/claude-token-inspector/suggest-split.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 747 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 $0.00048 $0.00747
Opus 5 $0.00024 $0.00374
Sonnet 5 $0.00010 $0.00149
Haiku 4.5 $0.00005 $0.00075

Measured 6d ago against content hash 0a9a5d59aa4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

suggest-split 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/suggest-split/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversation Split Advisor

Analyze the current conversation and determine whether it has drifted enough that starting a new session would meaningfully improve context quality.

Analysis process

  1. Map the conversation topics — scan the full history and identify distinct task areas or subject shifts. A "topic" is a coherent unit of work (e.g., "debugging the auth middleware", "writing README", "reviewing PR #42").

  2. Find the current task — what is the user actually working on right now? This is the anchor.

  3. Score past topics by carry-forward value:

    • Essential (carry forward): decisions made, constraints discovered, code written that is still active
    • Partial (summarize): context that's partially relevant but could be distilled to 2–3 sentences
    • Dead weight (discard): earlier topics completely unrelated to the current task
  4. Assess the split case — is there a clear turning point where the conversation shifted to the current task? If yes, that's the split candidate.

Output format

If a split is recommended:

✂️ Split recommended — conversation has drifted across {N} topic(s)

Then:

Topic map (chronological):

Turns Topic Status
1–8 Debugging login timeout 🗑️ Discard — resolved, no longer relevant
9–14 Reviewing PR #42 📋 Summarize — 2 decisions still apply
15–now Refactoring auth middleware ✅ This is your current task — carry forward

What to carry into the new conversation:

Write a ready-to-paste context block the user can paste at the start of their new session:

--- CONTEXT FROM PREVIOUS SESSION ---
[2–5 bullet points covering only the decisions, constraints, and code that are still relevant to the current task. Be specific: file names, function names, exact decisions made.]
--- END CONTEXT ---

Split instructions:

1. Copy the context block above
2. Start a new Claude Code session
3. Paste the context block as your first message
4. Continue with: [one sentence describing where to pick up]

Read the full file on GitHub · 86 lines

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 · 86 lines · 48 tokens per session scan A 0a9a5d59aa4c

Subscribe to this mod's changes

suggest-split is a skill published in the GitHub repository msiShariful/claude-token-inspector (4 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 747 once invoked, about $0.0002 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.