Ralph Orchestrator is a framework that repeatedly runs AI-agent tasks until they finish or reach an iteration limit. Developers use it to coordinate autonomous coding work through command-line, web-dashboard, and MCP-server interfaces, with state managed per workspace. The catalogue entries provide agent skills, agents, instructions, and plugins for operating Ralph.
Borrowing it
Nothing to install: this file belongs to mikeyobrien/ralph-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mikeyobrien/ralph-orchestrator/main/.claude/skills/find-code-tasks/SKILL.mdgit clone --depth 1 https://github.com/mikeyobrien/ralph-orchestratorWrote 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/skills/mikeyobrien/ralph-orchestrator/find-code-tasks)<a href="https://agentmods.dev/skills/mikeyobrien/ralph-orchestrator/find-code-tasks"><img src="https://agentmods.dev/badge/skills/mikeyobrien/ralph-orchestrator/find-code-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/skills/mikeyobrien/ralph-orchestrator/find-code-tasks"><img src="https://agentmods.dev/badge/skills/mikeyobrien/ralph-orchestrator/find-code-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 174 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00034 | $0.01290 |
| Opus 5.5 | $0.00014 | $0.00516 |
| Sonnet 5.5 | $0.00007 | $0.00258 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade B, and why
find-code-tasks 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 1mo 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- Check the script exists: `ls .claude/skills/find-code-tasks/task-status.sh` How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Code Tasks
Overview
This skill finds and displays all code tasks (.code-task.md files) in the repository, showing their frontmatter status and metadata. Use it to get a quick overview of pending work, find tasks by status, or check the state of the task backlog.
When to Use
- Starting a work session to see what tasks are available
- Checking status of tasks before/after running code-assist
- Finding tasks by status (pending, in_progress, completed)
- Getting a summary of task backlog
- Exporting task data for reporting
Parameters
-
filter (optional): Filter tasks by status
pending- Show only pending tasksin_progress- Show only in-progress taskscompleted- Show only completed tasks- (none) - Show all tasks
-
format (optional, default: "table"): Output format
table- Human-readable table with status symbolsjson- JSON array for programmatic usesummary- Counts by status only
-
tasks_dir (optional, default: ".ralph/tasks/"): Directory to search for tasks
Usage Examples
# Show all tasks in table format
/find-code-tasks
# Show only pending tasks
/find-code-tasks filter:pending
# Get JSON output for tooling
/find-code-tasks format:json
# Quick summary of task counts
/find-code-tasks format:summary
# Search custom directory
/find-code-tasks tasks_dir:tools/
Steps
1. Run Task Status Script
The script is colocated with this skill at .claude/skills/find-code-tasks/task-status.sh.
Execute it with appropriate arguments:
# Default: table format, all tasks
.claude/skills/find-code-tasks/task-status.sh
# With filter
.claude/skills/find-code-tasks/task-status.sh --pending
.claude/skills/find-code-tasks/task-status.sh --in_progress
.claude/skills/find-code-tasks/task-status.sh --completed
# With format
.claude/skills/find-code-tasks/task-status.sh --json
.claude/skills/find-code-tasks/task-status.sh --summary
# Custom tasks directory
TASKS_DIR=tools/ .claude/skills/find-code-tasks/task-status.sh
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 183 lines · 34 tokens per session scan B f20b3b34da4f
find-code-tasks is a skill published in the GitHub repository mikeyobrien/ralph-orchestrator (3,186 stars, last pushed 9d ago), licensed MIT. It adds 34 tokens to every session and 1,290 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gh-issues
Use when creating, triaging, or commenting on GitHub issues for the Kilo VS Code extension or JetBrains plugin via gh. Covers issue templates, project board assignment, title conventions, and required gh scopes.
nx-workspace
Nx workspace rules: running targets, affected commands, generators, project.json and the Nx MCP tools. Use when running or generating anything in an Nx monorepo, editing project.json, or reading its dependency graph.
trello-task-management
Trello cards, checklists and boards for kanban tracking. Use when creating or moving Trello cards, adding checklists, or tracking work on a Trello board.
jira-management
Jira issues, epics, sprints, backlog and workflow transitions. Use when creating or updating Jira issues, linking epics, moving work through a sprint, or searching the backlog.
ralph-linear
Fetch Linear tickets and build them with ralph-starter.
ralph-task
Manage tasks across GitHub and Linear with ralph-starter.