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.
/plugin marketplace add costajohnt/oss-autopilot/plugin install 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-guidelines)<a href="https://agentmods.dev/commands/costajohnt/oss-autopilot/oss-guidelines"><img src="https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/oss-guidelines/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/commands/costajohnt/oss-autopilot/oss-guidelines"><img src="https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/oss-guidelines.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00021 | $0.00868 |
| Opus 5 | $0.00010 | $0.00434 |
| Sonnet 5 | $0.00004 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
oss-guidelines scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/oss-guidelines [repo]
Surface for the per-repo guidelines machinery (#867 / #1283). Most users
land here after the extract-learnings workflow has run at least once
and want to read, edit, or reset what was stored — without re-running
the full extraction.
Inputs
[repo]— optional.owner/reposhorthand. When omitted, this command lists every repo with stored guidelines and asks which one the user wants to operate on.
What it does
Bundle freshness: the steps below prefer the MCP tools (no bundle needed). If you fall back to a
cli.bundle.cjscall, first ensure the bundle reflects the installed plugin version — the plugin ships no prebuilt bundle, so a stale one can persist after an update. Run"${CLAUDE_PLUGIN_ROOT}/scripts/build-cli-if-stale.sh" "${CLAUDE_PLUGIN_ROOT}"once before the first bundle call (exit 2 = build failed: stop and surface it). Skip this entirely when using the MCP tools.
-
Resolve the target repo.
- If an argument was passed, use it verbatim.
- Otherwise, enumerate repos with stored guidelines via the
mcp__plugin_oss-autopilot_oss-autopilot__guidelines-listtool when the MCP server is available, orcli.bundle.cjs guidelines list --jsonotherwise. Both return{ repos, count, storageMode }. Present the list viaAskUserQuestion. - If no guidelines exist for any repo, surface a one-line nudge
toward
extract-learningsand exit.
-
Render the current guidelines.
## Guidelines for {owner}/{repo} Stored: {byteSize} bytes, last updated {timestamp} {markdown content}Read via
mcp__plugin_oss-autopilot_oss-autopilot__guidelines-getwhen available; fall back tocli.bundle.cjs guidelines view --repo OWNER/REPO --jsonotherwise. -
Offer follow-up actions. Use
AskUserQuestion:- Re-extract from recent PRs — dispatches the
extract-learnings.mdworkflow scoped to this repo. - Edit guidelines — invokes the
edit-guidelines.mdworkflow (load → user edit → store, no extraction step). - Reset (delete) — calls
cli.bundle.cjs guidelines reset --repo OWNER/REPOafter a confirm prompt. Tombstones the entry in the gist (#867 semantics). - Done — exit cleanly.
- Re-extract from recent PRs — dispatches the
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 · 84 lines · 21 tokens per session scan A abe9c6eaed24
oss-guidelines is a command published in the GitHub repository costajohnt/oss-autopilot (12 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 868 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.
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).
content-start
Content production session start command. Gives the daily content session a structured start, shows pending work, and sets priorities.
ai-review
AI code review of the staged git diff via the Claude API.