QM is a shared work environment for coding agents that gives each employee and conversation an isolated workspace while allowing collaboration in Slack and on the web. Startups use it to run agents for individuals, teams, and company operations, with selectable harnesses and models. The catalogue entries extend QM with skills, instructions, and settings.
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 yc-software/qm --skill connect-appsgit clone --depth 1 https://github.com/yc-software/qmWrote 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/yc-software/qm/connect-apps)<a href="https://agentmods.dev/skills/yc-software/qm/connect-apps"><img src="https://agentmods.dev/badge/skills/yc-software/qm/connect-apps/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/yc-software/qm/connect-apps"><img src="https://agentmods.dev/badge/skills/yc-software/qm/connect-apps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 12 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00022 | $0.00651 |
| Opus 5.5 | $0.00009 | $0.00260 |
| Sonnet 5.5 | $0.00004 | $0.00130 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
connect-apps scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 28d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -X POST "$AGENT_API_URL/v1/connectors/oauth/consent/mint" \ How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connecting SaaS apps
Check Composio availability through GET /v1/composio/toolkits on the authenticated QM API. When available, load the composio skill and use its discovery and consent flow instead
of the direct OAuth flow below. An empty direct OAuth list or a native
oauth_not_configured error does not describe Composio availability. Preserve explicit
app restrictions and account permissions; never switch credentials to evade a denial.
When $AGENT_OAUTH_CONSENT_TOKEN is set you can help the user connect a SaaS app via a browser
consent link they tap — you never see or enter their password. The live Connected apps block is
the direct OAuth allowlist: offer direct OAuth links only for providers configured by the admin,
and offer no direct OAuth links when that list is empty. Mint a single-use link for the selected provider, then give the user the full URL to open:
curl -sS -X POST "$AGENT_API_URL/v1/connectors/oauth/consent/mint"
-H "X-Agent-Capability: $AGENT_OAUTH_CONSENT_TOKEN" -H 'content-type: application/json'
-d '{"provider":""}'
- The response has
connectUrl— give the user THAT exact URL (it is the full public tap-through link). Do NOT build it yourself or prepend$AGENT_API_URL— that private base isn't reachable from a browser. - If mint returns
oauth_not_configured, the native provider is not configured. Do not retry that direct OAuth path or re-send old links; this does not establish that every access path is unavailable. - You cannot open the link yourself; relay the URL, tell them to tap Allow, then return. After they connect, the app's tools/skills work in your 1:1s with them.
Connect a personal Slack account
When someone asks to connect Slack or use their existing web connectors from Slack, offer the personal Slack linking widget in web chat, or direct them to QM web Settings (/?view=settings) and Link your Slack account from Slack. They must sign in with their existing web account before connecting. This authorizes personal Slack access and links their verified Slack identity to that QM account. Workspace bot installation is separate. Do not create a generic Composio Slack link or infer identity from matching emails.
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.
- 28d ago Changed · -1 lines d94fde492f8f
- 1mo ago Changed · +6 lines cfefdbcc4094
- 1mo ago Changed 46a5942f19b1
- 1mo ago Changed 79f676d14867
- 1mo ago Changed · +6 lines 826bbabbfce6
- 1mo ago First seen · 23 lines · 22 tokens per session scan A db8dc8118970
connect-apps is a skill published in the GitHub repository yc-software/qm (15,486 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 651 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
lobster
Lobster executes multi-step workflows with approval checkpoints. Use it when.
facetime
Inspect FaceTime internal stages, place an approved call to a configured owner handle, and request hangup through facetimecall.
migrating-openai-agents-sdk-to-pydantic-ai
Migrate Python OpenAI Agents SDK applications to Pydantic AI and, when warranted, Pydantic AI Harness. Use for agents.Agent, Runner, function tools, handoffs, guardrails, sessions, human approval, streaming, or SandboxAgent. Do not use for applications built directly on the OpenAI Responses API without the Agents SDK…
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…