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/costajohnt/oss-autopilotWrote 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/costajohnt/oss-autopilot/oss-help)<a href="https://agentmods.dev/commands/costajohnt/oss-autopilot/oss-help"><img src="https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/oss-help.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00883 |
| Opus 5 | $0.00009 | $0.00441 |
| Sonnet 5 | $0.00003 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade B, and why
oss-help 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 today.
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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
Print this reference card for the user. Do NOT run any commands — just display the information below. How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSS Autopilot Quick Reference
Print this reference card for the user. Do NOT run any commands — just display the information below.
Commands
| Command | Purpose |
|---|---|
/oss |
Daily check — fetches open PRs, shows status dashboard, suggests actions (respond to reviews, fix CI, rebase, find new issues) |
/oss-search |
Find issues — multi-strategy search across GitHub for contributable issues matching your language/label preferences |
/oss-overnight |
Overnight run — unattended prepare-and-queue: same check as /oss, fix branches prepared in local worktrees, morning report in ~/.oss-autopilot/reports/; never pushes, posts, or merges |
/setup-oss |
Configure — set GitHub username, languages, labels, PR limits, and other preferences |
/oss-dashboard |
Dashboard — open the interactive SPA dashboard in your browser |
/oss-guidelines |
Guidelines — view, edit, or reset per-repo contribution guidelines learned from past PRs |
/pr-ready |
Pre-push gate — run the lint/test/review convergence loop to decide whether the current branch is ready to push |
/plan-ready |
Plan gate — run the same review-and-critique convergence loop on an implementation plan before code is written |
/oss-help |
This card — quick reference for all plugin capabilities |
Agents
These agents activate automatically when relevant, or you can ask for them directly:
| Agent | When to Use |
|---|---|
| pr-responder | "Help me respond to comments on my PR" — drafts professional replies to maintainer feedback |
| pr-health-checker | "Why is my PR failing CI?" — diagnoses CI failures, merge conflicts, stale reviews, and performs rebases |
| pr-compliance-checker | "Check if my PR is ready" — validates against opensource.guide best practices before submission |
| issue-scout | "Find me issues to work on" — searches and vets good contribution opportunities |
| repo-evaluator | "Is this repo worth contributing to?" — analyzes maintainer responsiveness and project health |
| contribution-strategist | "How am I doing?" — analyzes contribution patterns and provides strategic advice |
| pre-commit-reviewer | "Review my changes before I push" — checks diffs for bugs, style issues, and dead code |
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.
- today Changed · -2 lines 4889cf3223bd
- 7d ago First seen · 73 lines · 17 tokens per session scan B 087ad0deb2d3
oss-help is a command published in the GitHub repository costajohnt/oss-autopilot (12 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 883 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
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.
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.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
afo
Open feature worktree in terminal and start agent (shortcut for feature-open).
pick-agent
A command that helps users choose and import only the agent role they need, such as a frontend developer, researcher, or editor.
test
Generate tests for the specified code or feature.