oss

oss is a command for Claude Code from costajohnt/oss-autopilot. It costs 15 tokens per session (5,048 once invoked), scanned A, original, MIT.

A daily command for reviewing open-source pull requests and deciding what needs attention. It uses command-line tools to gather structured information and can route different tasks to specialized helpers.

In plain words
What is it for?
Use it to review open pull requests, search for contribution opportunities, investigate selected issues, and work through several issues with parallel investigation followed by ordered actions.
Why use it?
It gives developers one regular place to see pending work instead of manually checking every pull request. It can guide them through investigating issues, choosing tasks, and continuing contribution work.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the oss-autopilot plugin — 3 skills, 8 commands, 7 agents, 2 MCP servers 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 costajohnt/oss-autopilot
Claude Code
/plugin install oss-autopilot

Made for: Claude Code.

Or install oss-autopilot, the plugin that ships this one along with the rest of its 3 skills, 8 commands, 7 agents, 2 MCP servers.

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 oss

README.md
[![agentmods](https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/oss.svg)](https://agentmods.dev/commands/costajohnt/oss-autopilot/oss)
Your own site
<a href="https://agentmods.dev/commands/costajohnt/oss-autopilot/oss"><img src="https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/oss.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,048 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 $0.00015 $0.05048
Opus 5 $0.00008 $0.02524
Sonnet 5 $0.00003 $0.01010
Haiku 4.5 $0.00002 $0.00505

Measured 6d ago against content hash c818009ac0a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

oss 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.

commands/oss.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OSS Autopilot Daily Check

This command checks your open source PRs and provides a summary of what needs attention.

Workflow Architecture

This command (oss.md) is the core router that orchestrates the entire flow. It delegates complex actions to external workflow files:

/oss (this file)
 │
 ├─ Startup ──► workflows/startup-and-build.md
 │   Build CLI, run startup command, parse output, error recovery
 │
 ├─ Summary ─── First-Run Welcome (if no PRs)
 │
 ├─ Action Menu ──► workflows/action-menu.md
 │   Display PRs, present menu, parse input ───┐
 │                                              │
 │   ┌─────────────────────────────────────────┘
 │   │
 │   ├─ "Work through all issues" ──► workflows/work-through-issues.md
 │   │   Parallel investigation → consolidated results → sequential execution
 │   │
 │   ├─ "Pick from your issue list" ──► workflows/work-through-issues.md
 │   │   Display curated list → vet → implement → draft-first workflow
 │   │
 │   ├─ Specific PR (via "Other") ──► workflows/work-through-issues.md
 │   │   Dispatch agents for selected PRs only
 │   │
 │   ├─ "Search for new issues" ──► /oss-search command
 │   │   Parallel multi-strategy search with vetting
 │   │
 │   ├─ "Review issue replies" ──► workflows/review-issue-replies.md
 │   │   Issue reply triage handler
 │   │
 │   ├─ "Follow up on dormant PRs" ──► workflows/dormant-pr-follow-up.md
 │   │   Surface waiting-on-maintainer PRs past the 7/14/30-day cadence and draft
 │   │   a polite follow-up via the draft-review-post skill (user posts themselves)
 │   │
 │   └─ "Done for now" ──► Session End
 │
 ├─ Pre-Commit Review (after any code changes) ──┐
 │   │                                             │
 │   ├─ New contribution? ──► workflows/draft-first-workflow.md
 │   │   Steps 1-10: pre-flight → commit → review → integration check →
 │   │   manual testing → human review → squash → push + create PR → compliance → list update
 │   │
 │   └─ Existing PR update? ──► workflows/pre-commit-review.md
 │       Gather diff → dispatch review agents → consolidate → commit/push → post comment
 │
 └─ Session End

Read the full file on GitHub · 368 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 · 368 lines · 15 tokens per session scan A c818009ac0a3

Subscribe to this mod's changes

oss is a command published in the GitHub repository costajohnt/oss-autopilot (12 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 5,048 once invoked, about $0.0001 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.