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 cardstack/boxel --skill software-factory-operationsgit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/software-factory-operations)<a href="https://agentmods.dev/skills/cardstack/boxel/software-factory-operations"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/software-factory-operations/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/cardstack/boxel/software-factory-operations"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/software-factory-operations.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 | $0.00042 | $0.02806 |
| Opus 5.5 | $0.00017 | $0.01122 |
| Sonnet 5.5 | $0.00008 | $0.00561 |
| Haiku 4.5 | $0.00004 | $0.00281 |
Grade A, and why
software-factory-operations 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 5d 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.
as green. **Never curl/HTTP-poll the realm for files you just wrote** How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Factory Operations (V2 — lean, design-first)
You operate inside the factory execution loop. Workspace files live in a
local mirror of the target realm that the orchestrator syncs back
between iterations; your working directory is that mirror, so
realm-relative paths (song.gts, Song/one.json) resolve directly with
the native Read / Write / Edit / Glob / Grep / Bash tools.
This skill is deliberately small. Most knowledge loads on demand, two equivalent ways:
- Files (preferred for discovery): the full skill catalog lives at
.claude/skills/<name>/in your workspace — SKILL.md overviews plusreferences/*.mddeep docs.Glob/Grep/Readthem like any project:Grep -ri 'fitted' .claude/skillsfinds the doc you didn't know existed. When unsure whether guidance exists for something you're about to build, grep here FIRST. - Tools:
list_skillsfor the catalog,read_skill({ name })/read_skill({ name, reference })for targeted loads.
Load what the current work touches, nothing more.
When you need X, read Y
| Need | read_skill |
|---|---|
| Card/field authoring, CardDef/FieldDef syntax, formats | boxel (then specific references/*.md) |
| Fitted-format layout rules | boxel reference fitted-formats.md |
| Theme tokens / design-system CSS | boxel reference theme-design-system.md |
Search query syntax (boxel search --query) |
boxel-api |
Host commands via boxel run-command |
boxel-command |
| File-backed fields (images, files, csv) | boxel-file-def |
| Catalog Spec conventions | boxel reference spec-usage.md |
| Whether the catalog already has the card, field, component or command | catalog-reuse |
| Reusable UI components before hand-rolling any UI | boxel-ui-component-discovery |
| What card code can reach (host tools, boxel-ui, runtime-common, AI services) + import paths | boxel-runtime-surfaces |
Search-driven home/app cards, searchResultsComponent wire-query contract, live feeds |
boxel-live-surfaces |
Embedding child cards (<@fields.X @format=… />), format choice, container chrome |
boxel-delegated-render-control |
| fetch/auth from card code (store APIs vs raw fetch vs request-forward proxy) | boxel-fetch-contexts |
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.
- 5d ago First seen · 181 lines · 42 tokens per session scan A 9b1a1a645956
software-factory-operations is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 2,806 once invoked, about $0.0002 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 2026-10-21.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…