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.
git clone --depth 1 https://github.com/ruvnet/ruv-FANNWrote 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.
[](https://agentmods.dev/commands/ruvnet/ruv-fann/tasks)<a href="https://agentmods.dev/commands/ruvnet/ruv-fann/tasks"><img src="https://agentmods.dev/badge/commands/ruvnet/ruv-fann/tasks/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ruvnet/ruv-fann/tasks"><img src="https://agentmods.dev/badge/commands/ruvnet/ruv-fann/tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00479 |
| Opus 5 | $0.00000 | $0.00239 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
tasks 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 12d 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.
What it actually says
/github tasks
Lists all available tasks that can be claimed by swarms, sorted by priority.
Usage
/github tasks [options]
Options
--priority <level>- Filter by priority (critical, high, medium, low)--area <component>- Filter by area (core, mcp, neural, wasm, docs)--type <type>- Filter by type (bug, feature, task, enhancement)--limit <number>- Limit results (default: 20)
Examples
/github tasks # All available tasks
/github tasks --priority high # Only high priority tasks
/github tasks --area neural # Neural network related tasks
/github tasks --type bug # Only bug fixes
Implementation
Uses GitHub MCP to:
- Query issues with
availablelabel - Exclude issues with
swarm-claimedlabel - Sort by priority and creation date
- Format for easy reading
Example Output
📋 Available Tasks (12 total)
🔴 CRITICAL (2):
#62 [BUG] Memory leak causing crashes after 1 hour
Labels: bug, area: neural, priority: critical
Created: 2 hours ago
#61 [BUG] WASM module fails to load in production
Labels: bug, area: wasm, priority: critical
Created: 5 hours ago
🟠 HIGH (5):
#58 [FEATURE] Implement persistent memory storage
Labels: feature, area: core, priority: high
Created: 1 day ago
#57 [TASK] Add comprehensive integration tests
Labels: task, area: tests, priority: high
Created: 1 day ago
[... more tasks ...]
To claim a task: /github claim <number>
Task Format
Each task shows:
- Issue number and title
- Type indicator ([BUG], [FEATURE], [TASK])
- Labels for area and priority
- Age of the issue
- Brief description if available
Related Commands
/github claim <number>- Claim a specific task/github status- See overall coordination status/github my-tasks- Show your current tasks
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.
- 12d ago First seen · 76 lines · 0 tokens per session scan A faf37654f25e
tasks is a command published in the GitHub repository ruvnet/ruv-FANN (380 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 479 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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
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.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.