agentmods.dev

research-queue

A command that shows the status of a shared first-in, first-out research queue, which controls the order of concurrent research tasks. It reports active, waiting, and recently finished or failed runs.

In plain words
What is it for?
Use it to see whether research is running, what tasks are waiting, how long they have waited, and whether recent runs produced errors or timeouts.
Why use it?
It makes research delays and failures visible when several sessions are using the same queue. It also shows current queue depth and daily activity.

Command

57 8d ago B scan 0 tokens original MIT
View the source file intellegix/intellegix-code-agent-toolkit
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/intellegix/intellegix-code-agent-toolkit/research-queue
Clone the repo
git clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkit
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 603 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00603
Opus 5 $0.00000 $0.00302
Sonnet 5 $0.00000 $0.00121
Haiku 4.5 $0.00000 $0.00060

Measured 2d ago against content hash e9017b1ebdf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

research-queue scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

3. **For deeper history**, read the tail of `~/.claude/council-logs/perplexity-activity.jsonl` —
commands/research-queue.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/research-queue — Live Perplexity Research Queue Status

Show the current state of the global Perplexity research FIFO queue — the cross-session serialization layer that all concurrent /research-perplexity runs pass through. Use this to see what's running, who's waiting and where, and whether anything is failing.

What to do

  1. Read the live snapshot: ~/.claude/council-logs/perplexity-queue.json (atomically written; has a monotonic version — if you read it twice, trust the higher version).

    • If the file does not exist: no research has run through the queue yet — say so and stop.

  2. Render a compact status:

    • Active: the currently-running run — session, query preview, elapsed_s, heartbeat_age_s. If active is null → "idle (no run in progress)".
    • Queued (FIFO order): each waiting run — position, session, query preview, wait_s. Empty list → "none waiting".
    • Recent: the last few completed/error/timeout runs with duration_s and status.
    • Stats: depth (currently waiting), total_today, errors_today.

  3. For deeper history, read the tail of ~/.claude/council-logs/perplexity-activity.jsonl — the append-only event log (enqueued/started/completed/error/timeout), each line carrying a shared run_id that links to instrumentation-query.jsonl and runs.jsonl.

  4. Flag anything unhealthy and suggest a fix:

    • Active run with heartbeat_age_s > 120s → likely stalled/dead holder (the queue auto-reclaims via PID-liveness + TTL, but surface it).
    • Deep queue (many waiting) → congestion; expected under heavy concurrency.
    • Recent error/timeout events → check the keeper/session health.
    • If the queue is misbehaving, the instant kill-switch is RESEARCH_QUEUE_ENABLED=0 (runs then pass straight through, no queuing), and RESEARCH_QUEUE_MAX_WAIT (default 1200s) bounds the wait.

Notes

  • Source of truth is the ticket dir ~/.claude/config/research-queue/tickets/; the JSON is a derived snapshot. If the JSON looks stale, list the ticket dir to cross-check.
  • The research_queue_status MCP tool (browser-bridge) returns the same snapshot programmatically.
  • Architecture + operations: ~/.claude/docs/plans/2026-07-11-perplexity-research-queue-design.md.

Read the full file on GitHub · 38 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 · 38 lines · 0 tokens per session scan B e9017b1ebdf8

Subscribe to this mod's changes

research-queue is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 603 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ProductivityResearchagentic-aiai-agentsanthropicautomationclaudeclaude-code
Related

Other commands, from other repositories

README

Git workflow and quality assurance commands for the claude-skills repository.

alirezarezvani/claude-skills · 0 tokens

agentlas-cloud

Staff a task only from the signed-in owner's Agent Cloud agents.

agentlas-ai/Agentlas-OS · 13 tokens

dispatcher

Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.

Kanevry/session-orchestrator · 31 tokens

tldr

Re-apply TLDR rules for this turn (verdict first, no filler).

0p9b/TLDR · 17 tokens

execute

Interactive workflow for workspace isolation, pane-delegated implementation, testing, review, and cleanup.

transparent-pegasus/herdrpowers · 18 tokens

me-figure-discussion

Write or review thermal-fluid figure discussion with observation, physical mechanism, comparison, uncertainty, and claim limits.

hanhuark/mechanical-engineering-research-skill · 21 tokens