agentmods.dev

audit

audit is a command for coding agents from sourikduttanyu/astral. It costs 16 tokens per session (408 once invoked), scanned A, original, MIT.

A read-only audit command for finding installed agents and skills that are never used or have gone stale.

In plain words
What is it for?
It analyzes usage records, groups add-ons as never used, stale, or active, estimates saved tokens per session, and provides commands for disabling selected items.
Why use it?
It shows which add-ons consume context space without helping your work, so you can decide what to disable. Disabling moves files to a reversible folder instead of deleting them.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the astral plugin — 5 commands, 3 hooks, 1 MCP server shipped together

not rated 1 2mo ago A scan 16 tokens original MIT
View the source file 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.

agentmods
npx agentmods add commands/sourikduttanyu/astral/audit
Clone the repo
git clone --depth 1 https://github.com/sourikduttanyu/astral

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.

agentmods badge for audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/sourikduttanyu/astral/audit.svg)](https://agentmods.dev/commands/sourikduttanyu/astral/audit)
Your own site
<a href="https://agentmods.dev/commands/sourikduttanyu/astral/audit"><img src="https://agentmods.dev/badge/commands/sourikduttanyu/astral/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 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 $0.00016 $0.00408
Opus 5 $0.00008 $0.00204
Sonnet 5 $0.00003 $0.00082
Haiku 4.5 $0.00002 $0.00041

Measured 5d ago against content hash 36d4d4e87fcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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.

commands/audit.md · 41 lines

What it actually says

Astral audit. Goal: surface agents/skills that load into context every session but are never (or rarely) used, and help the user shed them to reclaim token budget. Read-only analysis; cleanup is reversible and user-approved.

  1. Run the audit script and show the user its report:

    python3 ${CLAUDE_PLUGIN_ROOT}/scripts/astral_audit.py

    (If CLAUDE_PLUGIN_ROOT is unset because this was installed via the one-line installer, use ~/.claude/astral/scripts/astral_audit.py.)

    It buckets every installed agent/skill into NEVER / STALE(>ASTRAL_STALE_DAYS, default 60) / ACTIVE, by parsing real usage from ~/.claude/projects/*/*.jsonl, and prints the reclaimable tokens/session.

  2. Summarize: how many prunable, how many tokens reclaimed, name the heaviest never-used ones.

  3. Use AskUserQuestion (multiSelect) to let the user choose what to shed:

    • all NEVER-used
    • NEVER + STALE
    • pick a specific subset
    • nothing (just wanted the report)

  4. For the chosen items, hand the user the ready-to-run mv ... .disabled/ commands from the script output (or --json for the full list). These MOVE files to a .disabled/ sibling dir - reversible, nothing deleted.

  5. Tell the user: this is reversible (move back from .disabled/), and they must restart Claude Code (or /hooks) for the picker to drop them. Do NOT run the mv commands yourself unless the user explicitly says to - this touches their global ~/.claude config.

Keep it tight.

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. 5d ago First seen · 41 lines · 16 tokens per session scan A 36d4d4e87fcb

Subscribe to this mod's changes

audit is a command published in the GitHub repository sourikduttanyu/astral (1 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 408 once invoked, about $0.0001 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.

Building agentsLLMclaude-codeclaude-code-plugincontext-managementdeveloper-toolsmcp-server
Related

Other commands, from other repositories

smartcompact

Pin important turns before compacting — pins survive compaction via SessionStart hook reinjection.

codeprakhar25/smartcompact · 17 tokens

recall-maintain

Run maintenance on the memory system. Primary function: pressure-based demotion when working memory exceeds the word budget. Secondary: stale entry verification, contradiction checks, open loop review.

davegoldblatt/total-recall · 0 tokens

recall-init-ids

Add ^tr IDs to untagged memory entries in managed files. This is safe to run multiple times - it only tags entries that don't already have IDs.

davegoldblatt/total-recall · 0 tokens

recall-init

Initialize the Total Recall memory system in this project.

davegoldblatt/total-recall · 0 tokens

recall-write

Write a note to memory, applying the write gate. Default destination: daily log.

davegoldblatt/total-recall · 0 tokens

recall-promote

Review recent daily logs and surface candidates for promotion to registers or CLAUDE.local.md.

davegoldblatt/total-recall · 0 tokens