A command for searching GitHub for open-source issues that may be worth contributing to. GitHub is a website where developers host code, track issues, and review proposed changes.

Use it to search for suitable issues across repositories, review pre-vetted issues when available, run broader searches when needed, and assess candidates before choosing one to work on.

It narrows a large set of public issues using contribution history, repository activity, maintenance signals, duplicate filtering, spam filtering, and issue vetting. This makes the search more focused than browsing issue lists manually.

oss-search — Command for Claude Code by costajohnt

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, 9 commands, 8 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/oss-search/github.svg)](https://agentmods.dev/commands/costajohnt/oss-autopilot/oss-search)

Your own site

<a href="https://agentmods.dev/commands/costajohnt/oss-autopilot/oss-search"><img src="https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/oss-search/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/costajohnt/oss-autopilot/oss-search"><img src="https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/oss-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,175 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.03175
Opus 5	$0.00009	$0.01588
Sonnet 5	$0.00004	$0.00635
Haiku 4.5	$0.00002	$0.00317

Measured 9d ago against content hash c09e3f27c622, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

oss-search 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 9d 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-search.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OSS Issue Search

This command searches for new open source issues to contribute to by delegating to the @oss-scout/core package (via the CLI's search command). Scout runs a staged multi-phase search (merged-PR repos + open-PR repos → starred → broad → maintained) with built-in rate-limit budgeting, skip-list dedup, spam filtering, and vetting — there is no reason for this skill to duplicate any of that logic (#929).

Input validation: See "AskUserQuestion Validation Protocol" in workflows/reference.md.

Session State

Initialize on entry (reset each time):

searchRoundScores: number[] = [] (average vetting score per search round)

Inherited from /oss session (if invoked from there):

hasIssueList, availableCount, completedCount, issueListPath — curated issue list info

Pre-Search: Issue List Check

If hasIssueList is true and availableCount > 0, present a preamble before searching:

Use AskUserQuestion:

"Review from your curated list ({availableCount} available)" — "Pick from pre-vetted issues you've already researched"
"Search GitHub" — "Find new issues via oss-scout"
"Both — list first, then search" — "Review your list, then search for more"
"Done for now"

Route based on choice:

"Review from list" → this command requires /oss context. Tell the user: "Returning to /oss to browse your issue list." End this command; the parent /oss session handles "Pick Issue From List".
"Search GitHub" → continue with Run Search below
"Both" → show list first (return to /oss for "Pick Issue From List"), then continue with Run Search
"Done for now" → end this command. If invoked from /oss, return to the parent session. If standalone, exit.

Run Search

Pre-Search: Ensure the CLI bundle is current

The plugin ships no prebuilt bundle (packages/*/dist/ is gitignored), so a stale or missing cli.bundle.cjs from a previous version can persist in the plugin cache after an update. /oss rebuilds on startup, but this command runs the bundle directly — so rebuild it here first, or a freshly-updated plugin would run old code (e.g. the pre-1-10 grade or pre-skip-list-fix behavior). Run the canonical helper before any bundle invocation:

Read the full file on GitHub · 238 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.

9d ago First seen · 238 lines · 18 tokens per session scan A c09e3f27c622

Subscribe to this mod's changes

oss-search is a command published in the GitHub repository costajohnt/oss-autopilot (13 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 3,175 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.

Claude Code Research TypeScript cli developer-tools github open-source

devbox-entrypoint

Context: runloop resumes a devbox by re-running the same entrypoint script, which invokes cn serve --id .... Because the entrypoint always replays, the CLI must avoid duplicating state on restart.

continuedev/continue · 0 tokens

atomic-plan

Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.

damusix/atomic-claude · 54 tokens

oss-search