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 agentmods add skills/binary16labs/prime-silo/devops-pipelinenpx skills add binary16labs/prime-silo --skill devops-pipelinegit clone --depth 1 https://github.com/binary16labs/prime-siloWhat 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 | $0.00075 | $0.01673 |
| Opus 5 | $0.00037 | $0.00837 |
| Sonnet 5 | $0.00015 | $0.00335 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
devops-pipeline 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 3d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prime-Silo DevOps pipeline
Prime-Silo packages as an Electron desktop app ("Space Agent") via electron-builder.
Two product layers ship together: the Space-Agent shell (Node server + browser UI, run
in-process) and the Benny runtime (Python + Neo4j + JRE) which is either bundled
(zero-install) or driven from an external $BENNY_HOME.
All commands run from the repo root: C:\Users\nsdha\OneDrive\binary16\prime-silo.
0. One-time: install packaging deps
electron + electron-builder live under packaging/. If packaging/node_modules is
missing, run first:
npm run install:packaging
1. Build types (pick the lightest that proves what you need)
| Goal | Command | Output | Notes |
|---|---|---|---|
| Fast shell-only test (validates main/tray/pet/UI changes) | npm run desktop:pack |
dist/desktop/windows/win-unpacked/Space Agent.exe |
No runtime bundle. Quick. Best for verifying desktop/main-process changes. |
| Zero-install local test (shell app) | npm run desktop:localtest |
dist/desktop/windows/win-unpacked/Space Agent.exe |
Builds + signs the shell app only. NOTE: it sets PRIME_SILO_BUNDLE_RUNTIME=1 but that env var is read nowhere since v1.2.9 — the runtime bundle was decoupled from the installer, so this does NOT assemble Python/Neo4j/JRE or run pip. Use the row below for the runtime bundle. |
| Runtime bundle (the docling/torch/Neo4j artifact) | node packaging/scripts/pack-runtime-bundle.js |
dist/runtime-bundle/runtime-bundle-<plat>-<arch>.tar.gz (+ .sha256, .json) |
Assembles embedded Python + site/ (full pip tree incl. docling/torch — slow, multi-GB) + Neo4j + JRE, tars the release asset the app fetches on first launch. THIS is what to validate after changing BUNDLE_RUNTIME_REQUIREMENTS. ~909 MB (2026-06). |
| Windows installer | npm run package:desktop:windows |
NSIS installer in dist/ |
Full build. |
| All Windows arches | npm run package:desktop:windows:all |
x64 + arm64 | |
| macOS / Linux | npm run package:desktop:{macos,linux}[:all] |
dmg+zip / AppImage | Run on the target OS. |
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.
- 3d ago First seen · 121 lines · 75 tokens per session scan A 00cb68b78a2f
devops-pipeline is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 10d ago), licensed MIT. It adds 75 tokens to every session and 1,673 once invoked, about $0.0004 per session on Opus 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
release
Dispatch a Chamber release build to either the insiders channel (Azure blob, Windows + macOS, invite-only testers) or the stable channel (public GitHub Releases, Windows + macOS). Use this skill whenever the user asks to release, cut, publish, promote, ship a build, push to insiders, send to testers, go public, or…
git-cliff
Use when the user wants to generate a changelog, create release notes from git history, update CHANGELOG.md before tagging a release, produce a changelog from conventional commits, or summarize commits since the last tag.
gh
Use when the user works with GitHub from the command line - listing or viewing pull requests, creating PRs and issues, reviewing or merging, watching workflow runs, downloading release assets, or hitting the REST/GraphQL API.
release-new-version
Release a new desktop stable version for Anarlog. Use when asked to cut, publish, or prepare a new stable desktop release after checking and merging the changelog.
new-changelog
Create the next desktop changelog entry when asked to add a changelog file or prepare the next release note under packages/changelog/content. Use this when the task is specifically about determining the next version and creating the markdown entry.
publish
Publish the Octop Python package: cut a release branch from develop, bump version, update CHANGELOG, open a PR to main; after merge, Actions tag on main (PyPI / Docker Hub) and sync main into develop. Use when the user asks to publish, release, bump version, cut a release, or run /publish.