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 skills add SummerRiversound/expo-launchpad --skill expo-launchpad-statusgit clone --depth 1 https://github.com/SummerRiversound/expo-launchpadWrote 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/skills/summerriversound/expo-launchpad/expo-launchpad-status)<a href="https://agentmods.dev/skills/summerriversound/expo-launchpad/expo-launchpad-status"><img src="https://agentmods.dev/badge/skills/summerriversound/expo-launchpad/expo-launchpad-status/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/skills/summerriversound/expo-launchpad/expo-launchpad-status"><img src="https://agentmods.dev/badge/skills/summerriversound/expo-launchpad/expo-launchpad-status.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 | $0.00027 | $0.00900 |
| Opus 5.5 | $0.00011 | $0.00360 |
| Sonnet 5.5 | $0.00005 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
expo-launchpad-status 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 2mo 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
expo-launchpad-status
Read-only status reporter for the expo-launchpad pipeline. Reads docs/harness/state.md and
docs/harness/pipeline-log.md and prints a summary of the current pipeline state.
All file schemas are defined in docs/harness-protocol.md — refer to §2 (state.md schema) and
§6 (log table schemas) as the single source of truth. Do not redefine schemas here.
This skill is strictly read-only. It must never modify state.md, pipeline-log.md, or any
other harness file, and takes no action beyond printing a report.
Input
docs/harness/ lives at the workspace root — the directory the pipeline was invoked from —
for the entire pipeline, never inside the generated <app_slug>/ project. Locate
docs/harness/state.md relative to the current working directory (the invocation dir), the same
convention every other phase skill uses.
If docs/harness/state.md does not exist, print:
No expo-launchpad run in this directory.
Then exit without error — do not create any file, do not treat this as a failure.
Procedure
1. Read state.md
Read docs/harness/state.md and extract the following fields per the schema in
docs/harness-protocol.md §2:
status—running|paused|completedcurrent_phase— the currently executing (or last-active) phasecurrent_round— integer round counternext_role— skill role that runs nextpause_reason—""|rate_limit|manual_action|errorresume_attempts— integercheckpoint—""|6a|6b|6cupdated_at— ISO-8601 timestamp of last write
2. Read pipeline-log.md (if present)
If docs/harness/pipeline-log.md exists, read the last 5 rows (e.g. tail -n 5 docs/harness/pipeline-log.md) to give a recent event summary. If the file is absent or empty,
skip this section of the report.
3. Print status report
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
expo-launchpad pipeline status
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Status : <status>
Current phase : <current_phase>
Round : <current_round>
Next role : <next_role>
Checkpoint : <checkpoint, or "—" if blank>
Resume attempts: <resume_attempts>
Last updated : <updated_at>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
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.
- 2mo ago First seen · 109 lines · 27 tokens per session scan A debcf8b1d623
expo-launchpad-status is a skill published in the GitHub repository SummerRiversound/expo-launchpad (2 stars, last pushed 9d ago), licensed MIT. It adds 27 tokens to every session and 900 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
shared-space
Record and use a team knowledge base that lives outside the vault - a network drive, Google Drive, OneDrive or SharePoint folder. Survey mode reads the place and writes down how it is organised into projects/NNNN- /shared/; place mode says where a vault note belongs in it. Use when the user wants to register a team…
vault-setup
Set up a machine to work with a workhub vault - check/install required software (git, Node.js, Claude Code, OpenCode), initialize the vault if needed, wire up Claude plugins, and run the OpenCode sync scripts. Use when onboarding a new machine, after a fresh vault-init, or when the harness feels half-configured.
task-handoff
Decide whether a workhub task meant for an agent to work continues in this session or goes to a fresh one, and hand it off. Use right after filing such a task (task-list, task-report follow-ups), or when the user asks to run a task in another session.
task-chain
Run several workhub tasks back to back in this session, one subagent per task, with the owner's choices recorded up front. Use when the owner names an ordered list of tasks to work through (a milestone's run, a dependent series), not for a single task (task-handoff).
create-work-log
A tool that turns Git activity from configured repositories into a daily or weekly work log in Markdown. Git is a system that records changes to code, including who made them and when.
manage-backlog
Add, refine, split, or reorder PBIs in the file-based product backlog in the team-shared folder. Use when the user wants to create backlog items, write user stories or acceptance criteria, estimate points, split oversized items, or tidy the product backlog.