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.
Borrowing it
Nothing to install: this file belongs to yc-software/qm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yc-software/qm/main/.codex/skills/deploy-qm/SKILL.mdgit 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/deploy-qm)<a href="https://agentmods.dev/skills/yc-software/qm/deploy-qm"><img src="https://agentmods.dev/badge/skills/yc-software/qm/deploy-qm/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/deploy-qm"><img src="https://agentmods.dev/badge/skills/yc-software/qm/deploy-qm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00301 |
| Opus 5.5 | $0.00014 | $0.00120 |
| Sonnet 5.5 | $0.00007 | $0.00060 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
deploy-qm 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.
What it actually says
Deploy QM
Read ../../../deployment.md completely and follow it
as the authoritative workflow. Read only the selected provider reference. Read
references/email.md before collecting email secrets. Administrators can defer
email setup and use qm admin-login; ordinary email sign-in needs a transport. Read
references/slack.md only when Slack is requested.
A deployment needs a base model key and a way for people to sign in. Collect
both in the same pass. The base model provider is a deployment choice recorded
as modelProvider, not a setting to leave for the Admin page. Sign-in is either
the built-in auth broker, with optional email setup for an initial admin-only
deployment, or an external OIDC provider such as Slack. Read references/email.md
once the operator has chosen the broker.
Use the installed @yc-software/qm dependency through npm exec qm -- <command>. Do
not require or clone the QM source repository. Complete every acceptance check
and return the handoff required by deployment.md. Treat qm check --live and
its private live session canary as the automated release gate; still complete
the administrator's manual sign-in and web acceptance check.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +3 tokens per session d95131034a70
- 2mo ago Changed 7d190a957da9
- 2mo ago First seen · 26 lines · 31 tokens per session scan A b1f4f1f2c4a0
deploy-qm is a skill published in the GitHub repository yc-software/qm (15,646 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 301 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 2026-08-30.
deploy-qm compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deploy-qmyc-software/qm | Skill | 16k | today | MIT | A | 34 | Codex |
| node-inspect-debuggeropenclaw/openclaw | Skill | 394k | today | MIT | A | 28 | Claude Code, Codex |
| lobsteropenclaw/openclaw | Skill | 394k | today | MIT | A | 0 | Claude Code, Codex |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | today | MIT | A | 80 | Claude Code, Codex |
| knowledge-captureopenclaw/openclaw | Skill | 394k | today | MIT | A | 51 | Claude Code, Codex |
| knowledge-recallopenclaw/openclaw | Skill | 394k | today | MIT | A | 40 | Claude Code, Codex |
| migrating-openai-agents-sdk-to-pydantic-aipydantic/pydantic-ai | Skill | 21k | today | MIT | A | 87 | Codex |