A context-budget manager for coding-agent sessions. It tracks how much conversation space is being used and helps preserve summaries of completed work.

Use it to check context usage, save checkpoints, find stale agents or skills, and get suggestions before starting unrelated work.

Long sessions can run out of context or become cluttered with finished details. This helps identify work that can be removed from the active conversation.

help — Command for Claude Code by sourikduttanyu/astral

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/sourikduttanyu/astral

Made for: Claude Code.

Or install astral, the plugin that ships this one along with the rest of its 5 commands, 3 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/commands/sourikduttanyu/astral/help/github.svg)](https://agentmods.dev/commands/sourikduttanyu/astral/help)

Your own site

<a href="https://agentmods.dev/commands/sourikduttanyu/astral/help"><img src="https://agentmods.dev/badge/commands/sourikduttanyu/astral/help/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/sourikduttanyu/astral/help"><img src="https://agentmods.dev/badge/commands/sourikduttanyu/astral/help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 204 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.

Model	Per session	Once invoked
Fable 5.1	$0.00009	$0.00204
Opus 5.5	$0.00004	$0.00082
Sonnet 5.5	$0.00002	$0.00041
Haiku 4.5	$0.00001	$0.00020

Measured 2mo ago against content hash 9fd1e056d50f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

help 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 2mo 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.

commands/help.md · 18 lines

What it actually says

Show the user this quick reference (keep it short):

Astral — context-budget manager. Never hit autocompact; shed done work instead.

Runs automatically: warns at 40/55/70% context with what's DONE.
/astral:checkpoint — pick finished work to shed → writes durable summary + hands you a steered /compact line.
/astral:status — current context level + done vs in-flight.
/astral:audit — find never-used / stale agents + skills that bloat every session; prune them (reversible).
Large reads auto-suggest a subagent (keeps context lean).
Starting unrelated work → Astral suggests /clear first.

Tune via env: ASTRAL_WINDOW, ASTRAL_BUCKETS, ASTRAL_READ_TOKENS. Repo: https://github.com/sourikduttanyu/astral

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.

2mo ago First seen · 18 lines · 9 tokens per session scan A 9fd1e056d50f

Subscribe to this mod's changes

help is a command published in the GitHub repository sourikduttanyu/astral (1 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 204 once invoked, about $0.0000 per session on Opus 5.5. 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.

Building agents Claude Code LLM Productivity claude-code-plugin context-management developer-tools mcp-server

help next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
helpsourikduttanyu/astral	Command	1	4mo ago	MIT	A	9	Claude Code
recall-loopjoseairosa/recall	Command	178	11d ago	MIT	A	36	Claude Code
budgetegorfedorov/claude-context-optimizer	Command	130	10d ago	MIT	A	0	Claude Code
orchestrateegorfedorov/claude-context-optimizer	Command	130	10d ago	MIT	A	0	Claude Code
remembrall-helpcukas/remembrall	Command	6	3d ago	MIT	A	17	Claude Code
budgetcukas/remembrall	Command	6	3d ago	MIT	A	13	Claude Code
timeturnercukas/remembrall	Command	6	3d ago	MIT	A	20	Claude Code