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.
npx agentmods add commands/costajohnt/oss-autopilot/setup-ossgit 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/setup-oss)<a href="https://agentmods.dev/commands/costajohnt/oss-autopilot/setup-oss"><img src="https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/setup-oss.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 | $0.00009 | $0.02801 |
| Opus 5 | $0.00005 | $0.01401 |
| Sonnet 5 | $0.00002 | $0.00560 |
| Haiku 4.5 | $0.00001 | $0.00280 |
Grade A, and why
setup-oss scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSS Autopilot Setup
Customize your OSS Autopilot preferences. This is optional — the tool works out of the box with auto-detected settings. Use this command to fine-tune languages, labels, PR limits, and other preferences.
Input validation: See "AskUserQuestion Validation Protocol" in
workflows/reference.md.
Step 0: Ensure CLI is Built and Available
This flow delegates entirely to the CLI. There is no markdown-only fallback — if the CLI cannot be built, ask the user to install Node 22+ and re-run.
Build the CLI on first run (auto-installs deps). Delegates to scripts/build-cli-if-stale.sh (#1292), which detects an existing-but-stale bundle as well as a missing one — the prior existence-only check would happily reuse a bundle from a stale checkout:
CLI_HELPER_RC=0
"${CLAUDE_PLUGIN_ROOT}/scripts/build-cli-if-stale.sh" "${CLAUDE_PLUGIN_ROOT}" >/tmp/oss-setup-cli-build.log 2>&1 || CLI_HELPER_RC=$?
if [ "$CLI_HELPER_RC" = "2" ]; then
echo "BUILD_FAILED"; tail -5 /tmp/oss-setup-cli-build.log; exit 1
fi
If the build succeeded but the bundle file still isn't there, or if node is unavailable: Stop the flow and tell the user:
"OSS Autopilot setup needs the CLI. Install Node.js 22+ from https://nodejs.org, then re-run
/setup-oss. (Alternative: build manually withcd ${CLAUDE_PLUGIN_ROOT}/packages/core && npm install && npm run bundle.)"
If output starts with BUILD_FAILED: Show the error lines and the same install/re-run guidance. Common causes: missing Node 22+, stale node_modules, no network for npm install.
Then verify the CLI is callable:
node "${CLAUDE_PLUGIN_ROOT}/packages/core/dist/cli.bundle.cjs" checkSetup --json 2>/dev/null
If this also fails, surface the install/re-run guidance and stop.
Step 1: Check Current Status
Run the setup command to see current configuration:
node "${CLAUDE_PLUGIN_ROOT}/packages/core/dist/cli.bundle.cjs" setup --json 2>/dev/null
If setupComplete: true, ask:
"Setup is already complete. Would you like to reconfigure your settings?"
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.
- 5d ago First seen · 293 lines · 9 tokens per session scan A f559b322417c
setup-oss is a command published in the GitHub repository costajohnt/oss-autopilot (12 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 2,801 once invoked, about $0.0000 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.
Other commands, from other repositories
loci-sync
Sync information between this project and the Loci brain index. Keep full project memory in the project repo.
loci-scan
Refresh the current project's local Loci memory.
doc
Use this command to create a new feature doc, how-to, concept, reference, or troubleshooting guide — it scaffolds the file, frontmatter, structure, and sidebar entry.
claude-tracker
List and browse your saved Claude Code sessions with status (running/inactive/VS Code).
gov-reuse
Discover reusable UK government code before building from scratch.
INDEX
16 custom slash commands in /.claude/commands/.