history

history is a command for Claude Code from swoopeagle/standardgraph. It costs 0 tokens per session (739 once invoked), scanned A, original, MIT.

A command that collects job-run history from multiple pipeline machines into one timeline by reading their logs over SSH.

In plain words
What is it for?
Use it to review overnight, reingest, resume, and other pipeline runs on the configured Mac minis.
Why use it?
It makes it easier to see which jobs finished, failed, or have unclear results, along with their type, time, and reported counts.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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/swoopeagle/standardgraph/history
Clone the repo
git clone --depth 1 https://github.com/swoopeagle/standardgraph

Made for: Claude Code.

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 history

README.md
[![agentmods](https://agentmods.dev/badge/commands/swoopeagle/standardgraph/history.svg)](https://agentmods.dev/commands/swoopeagle/standardgraph/history)
Your own site
<a href="https://agentmods.dev/commands/swoopeagle/standardgraph/history"><img src="https://agentmods.dev/badge/commands/swoopeagle/standardgraph/history.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 739 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 $0.00000 $0.00739
Opus 5 $0.00000 $0.00369
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 5d ago against content hash d853ba124267, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

history 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.

.claude/commands/history.md · 60 lines

What it actually says

Show the job run history across all pipeline machines.

SSH into both Mac minis and parse their log directories into a unified timeline.

Run on Mac mini 2:

ssh [email protected] "
  echo '=== MINI2 ===' &&
  for f in \$(ls -t ~/projects/intl-math-standards-mcp/logs/*.log 2>/dev/null); do
    fname=\$(basename \$f)
    size=\$(wc -l < \$f)
    modified=\$(stat -f '%Sm' -t '%Y-%m-%d %H:%M' \$f)
    # Detect outcome
    if grep -q 'ALL DONE' \$f 2>/dev/null; then outcome='✓ done'
    elif grep -q 'FAILED' \$f 2>/dev/null; then outcome='✗ failed'
    elif grep -q 'Total:.*mappings written' \$f 2>/dev/null; then outcome='✓ done'
    else outcome='? unclear'; fi
    # Detect job type
    if echo \$fname | grep -q 'overnight'; then jtype='overnight'
    elif echo \$fname | grep -q 'reingest'; then jtype='reingest'
    elif echo \$fname | grep -q 'resume'; then jtype='resume'
    else jtype='other'; fi
    # Standards count if present
    standards=\$(grep -oE '[0-9]+ standards' \$f 2>/dev/null | tail -1 || echo '')
    echo \"\$modified | \$jtype | \$outcome | \$standards | \$fname\"
  done
"

Run on Mac mini 3:

ssh [email protected] "
  echo '=== MINI3 ===' &&
  for f in \$(ls -t ~/projects/intl-math-standards-mcp/logs/*.log 2>/dev/null); do
    fname=\$(basename \$f)
    modified=\$(stat -f '%Sm' -t '%Y-%m-%d %H:%M' \$f)
    if grep -q 'ALL DONE' \$f 2>/dev/null; then outcome='✓ done'
    elif grep -q 'FAILED' \$f 2>/dev/null; then outcome='✗ failed'
    elif grep -q 'Total:.*mappings written' \$f 2>/dev/null; then outcome='✓ done'
    else outcome='? unclear'; fi
    if echo \$fname | grep -q 'overnight'; then jtype='overnight'
    elif echo \$fname | grep -q 'reingest'; then jtype='reingest'
    elif echo \$fname | grep -q 'resume'; then jtype='resume'
    else jtype='other'; fi
    standards=\$(grep -oE '[0-9]+ standards' \$f 2>/dev/null | tail -1 || echo '')
    echo \"\$modified | \$jtype | \$outcome | \$standards | \$fname\"
  done
"

Present the combined output as a clean table sorted by date (newest first):

Date Machine Job type Outcome Standards

Then note:

  • Any failed jobs that should be re-run
  • The most recent successful run on each machine
  • Whether the two machines are in sync (same standards count)
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 · 60 lines · 0 tokens per session scan A d853ba124267

Subscribe to this mod's changes

history is a command published in the GitHub repository swoopeagle/standardgraph (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 739 tokens. 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 commands, from other repositories

setup-bigquery

Command "setup-bigquery" from minicoohei/ai-agent-camp, covering bigquery / gcp 認証セットアップ, step 0: セットアップ進捗の確認, このセッションでやること, 準備チェック and step 1: gcloud cli のインストール.

minicoohei/ai-agent-camp · 2 tokens

setup-elevenlabs.en

Command "setup-elevenlabs.en" from minicoohei/ai-agent-camp, covering elevenlabs api setup, step 0: check setup progress, what you'll do in this session, readiness check and step 1: open elevenlabs in the browser.

minicoohei/ai-agent-camp · 2 tokens

setup-elevenlabs.es

Command "setup-elevenlabs.es" from minicoohei/ai-agent-camp, covering configuración de la api de elevenlabs, step 0: verificar el progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: abrir elevenlabs en el navegador.

minicoohei/ai-agent-camp · 2 tokens

setup-elevenlabs

Command "setup-elevenlabs" from minicoohei/ai-agent-camp, covering elevenlabs api セットアップ, step 0: セットアップ進捗の確認, このセッションでやること, 準備チェック and step 1: ブラウザでelevenlabsを開く.

minicoohei/ai-agent-camp · 2 tokens

setup-fal.es

Command "setup-fal.es" from minicoohei/ai-agent-camp, covering configuración de la api de fal.ai, step 0: verificar el progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: abrir fal.ai en el navegador y crear una cuenta.

minicoohei/ai-agent-camp · 2 tokens

setup-fal

Command "setup-fal" from minicoohei/ai-agent-camp, covering fal.ai api セットアップ, step 0: セットアップ進捗の確認, このセッションでやること, 準備チェック and step 1: ブラウザで fal.ai を開いてアカウントを作成する.

minicoohei/ai-agent-camp · 2 tokens