discover-tasks

discover-tasks is a skill for Claude Code, Kiro from agent-sh/agentsys. It costs 55 tokens per session (2,464 once invoked), scanned A, original, MIT.

A task-discovery skill that finds open work from sources such as GitHub, GitLab, local task files, and custom sources, then ranks it for selection.

In plain words
What is it for?
Use it to discover open issues, find the next task, prioritize work, or list tasks from configured project sources.
Why use it?
It gathers possible work into one view and checks existing policy and claimed tasks before suggesting what to do next.

Skill for Claude CodeKiro

Written for Claude Code and Kiro: allowed-tools in frontmatter, but also installed under .kiro/. Also seen: names the AskUserQuestion tool; mentions OpenCode.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is // Path: skills/discover-tasks/ -> ../../lib/state/workflow-state.js.

Part of the agentsys plugin — 28 skills, 1 hook shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add agent-sh/agentsys
Claude Code
/plugin install agentsys

Made for: Claude Code, Kiro.

Or install agentsys, the plugin that ships this one along with the rest of its 28 skills, 1 hook.

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 discover-tasks

README.md
[![agentmods](https://agentmods.dev/badge/skills/agent-sh/agentsys/discover-tasks.svg)](https://agentmods.dev/skills/agent-sh/agentsys/discover-tasks)
Your own site
<a href="https://agentmods.dev/skills/agent-sh/agentsys/discover-tasks"><img src="https://agentmods.dev/badge/skills/agent-sh/agentsys/discover-tasks.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,464 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 $0.00055 $0.02464
Opus 5 $0.00028 $0.01232
Sonnet 5 $0.00011 $0.00493
Haiku 4.5 $0.00006 $0.00246

Measured 6d ago against content hash bfcb39b2b6cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

discover-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 6d 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.

.kiro/skills/discover-tasks/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

discover-tasks

Discover tasks from configured sources, validate them, and present for user selection.

When to Use

Invoked during Phase 2 of /next-task workflow, after policy selection. Also usable standalone when the user wants to discover and select tasks from configured sources.

Workflow

Phase 1: Load Policy and Claimed Tasks

// Use relative path from skill directory to plugin lib
// Path: skills/discover-tasks/ -> ../../lib/state/workflow-state.js
const workflowState = require('../../lib/state/workflow-state.js');

const state = workflowState.readState();
const policy = state.policy;

// Load claimed task IDs from registry (tasks[] contains worktree-manager claims)
const tasksRegistry = workflowState.readTasks();
const claimedIds = new Set(tasksRegistry.tasks.map(t => t.id));

Phase 2: Fetch Tasks by Source

Source types:

  • github / gh-issues: GitHub CLI
  • gh-projects: GitHub Projects (v2 boards)
  • gitlab: GitLab CLI
  • local / tasks-md: Local markdown files
  • custom: CLI/MCP/Skill tool
  • other: Agent interprets description

GitHub Issues:

# Fetch with pagination awareness
gh issue list --state open \
  --json number,title,body,labels,assignees,createdAt,url \
  --limit 100 > /tmp/gh-issues.json

GitLab Issues:

glab issue list --state opened --output json --per-page 100 > /tmp/glab-issues.json

Local tasks.md:

for f in PLAN.md tasks.md TODO.md; do
  [ -f "$f" ] && grep -n '^\s*- \[ \]' "$f"
done

GitHub Projects (v2):

// Extract gh-projects parameters from policy
const projectNumber = policy.taskSource.projectNumber;
const owner = policy.taskSource.owner;
if (!projectNumber || !owner) {
  throw new Error('gh-projects source missing projectNumber or owner in policy.taskSource');
}
# Requires 'project' token scope. If permission error: gh auth refresh -s project
gh project item-list "$PROJECT_NUMBER" --owner "$OWNER" --format json --limit 100 > /tmp/gh-project-items.json

Read the full file on GitHub · 298 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. 6d ago First seen · 298 lines · 55 tokens per session scan A bfcb39b2b6cc

Subscribe to this mod's changes

discover-tasks is a skill published in the GitHub repository agent-sh/agentsys (982 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 2,464 once invoked, about $0.0003 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 2026-08-30.