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.
git clone --depth 1 https://github.com/kouroshez/coding-osWrote 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/kouroshez/coding-os/new-project)<a href="https://agentmods.dev/commands/kouroshez/coding-os/new-project"><img src="https://agentmods.dev/badge/commands/kouroshez/coding-os/new-project/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/kouroshez/coding-os/new-project"><img src="https://agentmods.dev/badge/commands/kouroshez/coding-os/new-project.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 | $0.00000 | $0.00799 |
| Opus 5.5 | $0.00000 | $0.00320 |
| Sonnet 5.5 | $0.00000 | $0.00160 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
new-project 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.
What it actually says
Scaffold a new coding-os project non-interactively — the official agent recipe (TASK-359).
Steps:
- Discover what's available (read-only):
cos list-stacks --format json→ stacks (grouped bylanguage) +presets.cos skills-list --stack <id> --format json→ required/recommended/optional skills for a stack.
- Preview the composition BEFORE writing anything:
cos init --preset <id> --dry-config(or--template a --template b --dry-config)- Read the swimlane union and the reported merge conflicts (later stack wins). Nothing is written.
- Create in one shot (every Composer option has a flag — full parity, incl. multi-agent + module toggles):
cos init \
--agent claude \ # one+ adapters, comma-separated: --agent claude,codex
--preset nextjs-fastapi \ # OR: --template go-fiber --template fastapi
--name my-app -d /path/to/parent \ # omit --name only in interactive shells
--skills redis,docker \ # extra core skills (validated; see cos skills-list)
--profile standard \ # module surface: lite | core | standard (default) | full
--disable-module memory \ # optional, repeatable: turn a subsystem off at create
--summary "One to two paragraphs describing the product, its users, and what matters most." \
--yes --no-index
- Verify: exit code 0;
--format jsonemits the summary object (path,slug,agents,templates, …). The project self-registers in the hub;--summaryseedsdocs/_meta/project-description.md(the description→PRD intake) and leaves_TODO:markers in the seeded PRD, so the panel still offers the guided interview.
Rules:
- Non-TTY without
--yesfails fast naming the missing flags — never rely on prompts in automation. --presetand--templateare mutually exclusive; unknown skills/stacks/presets exit 2 listing what exists.--agenttakes one or more adapters (claude,codex), comma-separated — a project may host several.--profile <name>picks the module surface (cos init --helplists the live set fromsubsystems.yaml):lite= kernel only (discipline + safety, near-zero MCP tools — the MCP-averse adopter),core,standard(default:cognition+cicdoff),full= everything. Omitting it applies the registry default, so a project can end up leaner than you expected — pass it explicitly when the surface matters.--disable-module <id>(repeatable) turns one subsystem off; ids come fromsubsystems.yaml(docs,tasks,graph,memory,cognition,observability,hub-extras,cicd).kernelcan't be disabled and a module's dependents go with it (unknown/kernel exit 2).- Profile and
--disable-moduleare UNIONED — a profile can only ever remove more.--enable-module <id>(repeatable) is the escape: it force-enables a module after the union, pulls itsdepends_onchain in with it, and errors when the same id is also explicitly disabled; that is exactly what the Hub Composer sends for chips left on.cos module listshows the result. - Don't pass
--nameyou can't validate:^[a-z0-9][a-z0-9._-]{0,63}$.
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 · 34 lines · 0 tokens per session scan A fe1600ebecdb
new-project is a command published in the GitHub repository kouroshez/coding-os (7 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 799 tokens. 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.
new-project compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| new-projectkouroshez/coding-os | Command | 7 | today | Apache-2.0 | A | 0 | Claude Code |
| memorizelucasrosati/claude-code-memory-setup | Command | 1.1k | 17d ago | MIT | A | 0 | Claude Code |
| slm-governancequalixar/superlocalmemory | Command | 271 | 9d ago | AGPL-3.0 | A | 117 | GitHub Copilot |
| bootstrap-memory0xK3vin/MegaMemory | Command | 735 | 6mo ago | MIT | A | 0 | Claude Code |
| remembermajor7apps/pensyve | Command | 99 | yesterday | none | A | 11 | Claude Code |
| kg-setupEthics03/kgskill | Command | 3 | 7mo ago | MIT | A | 8 | Claude Code |
| gsd:reviewmrboups/xbrain | Command | 2 | 1mo ago | MIT | A | 19 | Claude Code |