devteam-logs

A log-viewing command for DevTeam execution records and event history. Logs are timestamped records that help show what the system and its agents did.

In plain words
What is it for?
Use it to view recent logs, follow the latest entries, filter errors or warnings, inspect one agent or session, and export records as text or JSON.
Why use it?
It makes troubleshooting easier by letting you narrow records to a session, agent, time range, or error level instead of searching everything manually.

Command

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/michael-harris/devteam/devteam-logs
Clone the repo
git clone --depth 1 https://github.com/michael-harris/devteam
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 1,842 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 $0.00000 $0.01842
Opus 5 $0.00000 $0.00921
Sonnet 5 $0.00000 $0.00368
Haiku 4.5 $0.00000 $0.00184

Measured 2d ago against content hash b35b8d312a13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devteam-logs 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 2d 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/devteam-logs.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevTeam Logs Command

Command: /devteam:logs [options]

View execution logs, event history, and debugging information.

Usage

/devteam:logs                      # Show recent logs
/devteam:logs --session <id>       # Show logs for specific session
/devteam:logs --agent <name>       # Filter by agent
/devteam:logs --level error        # Filter by log level
/devteam:logs --tail 50            # Show last 50 entries
/devteam:logs --export             # Export logs to file

Options

Option Description
--session <id> Filter by session ID
--agent <name> Filter by agent name
--level <level> Filter by level: debug, info, warn, error
--tail <n> Show last N entries (default: 20)
--since <time> Show logs since time (e.g., "1h", "30m")
--export Export to logs/devteam-TIMESTAMP.log
--json Output as JSON
--verbose Show full log details

Your Process

Step 1: Query Events Database

async function getLogs(options) {
    let query = `
        SELECT
            e.id,
            e.timestamp,
            e.event_type,
            e.data,
            s.command as session_command,
            ar.agent
        FROM events e
        LEFT JOIN sessions s ON e.session_id = s.id
        LEFT JOIN agent_runs ar ON e.session_id = ar.session_id
        WHERE 1=1
    `

    const params = []

    if (options.session) {
        query += ` AND e.session_id = ?`
        params.push(options.session)
    }

    if (options.agent) {
        query += ` AND ar.agent LIKE ?`
        params.push(`%${options.agent}%`)
    }

    if (options.level) {
        query += ` AND json_extract(e.data, '$.level') = ?`
        params.push(options.level)
    }

    if (options.since) {
        const sinceTime = parseTimeOffset(options.since)
        query += ` AND e.timestamp > datetime('now', ?)`
        params.push(sinceTime)
    }

    query += ` ORDER BY e.timestamp DESC LIMIT ?`
    params.push(options.tail || 20)

    return await db.all(query, params)
}

Read the full file on GitHub · 242 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. 2d ago First seen · 242 lines · 0 tokens per session scan A b35b8d312a13

Subscribe to this mod's changes

devteam-logs is a command published in the GitHub repository michael-harris/devteam (18 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,842 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 2026-08-30.