acr-explain

A command that replays the recorded activity of a completed ACR task, including its provider, token counts, duration, and events in time order.

In plain words
What is it for?
Use it to investigate a task by ID or find recent task IDs when none is supplied.
Why use it?
It makes a task’s result and execution history inspectable instead of leaving you to infer what happened.

Command for Claude Code

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/hbkdad/arc/acr-explain
Clone the repo
git clone --depth 1 https://github.com/hbkdad/arc

Made for: Claude Code.

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 189 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 $0.00189
Opus 5 $0.00008 $0.00095
Sonnet 5 $0.00003 $0.00038
Haiku 4.5 $0.00002 $0.00019

Measured 3d ago against content hash 3496dd5cacc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

acr-explain 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 3d 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.

.claude/commands/acr-explain.md · 9 lines

What it actually says

Run uv run acr explain $ARGUMENTS from the repo root and report what it shows: objective, final status, which provider handled it, token counts, total duration, and the chronological event sequence. If the task id doesn't exist, say so plainly -- don't guess at what a valid task might have looked like.

If $ARGUMENTS is empty, there's no dedicated acr tasks list command -- instead query the real tasks table directly (e.g. sqlite3 data/acr.db "select id, objective, status, created_at from tasks order by created_at desc limit 10", adjusting the db path from acr doctor's output if it differs) to show recent task ids so the user can pick one, rather than failing silently.

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. 3d ago First seen · 9 lines · 16 tokens per session scan A 3496dd5cacc1

Subscribe to this mod's changes

acr-explain is a command published in the GitHub repository hbkdad/arc (4 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 189 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.