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/philipyaz/cos/cos-setupnpx skills add philipyaz/cos --skill cos-setupgit clone --depth 1 https://github.com/philipyaz/cosWrote 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/philipyaz/cos/cos-setup)<a href="https://agentmods.dev/skills/philipyaz/cos/cos-setup"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/cos-setup.svg" alt="Measured on agentmods" 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 | $0.00167 | $0.12654 |
| Opus 5 | $0.00084 | $0.06327 |
| Sonnet 5 | $0.00033 | $0.02531 |
| Haiku 4.5 | $0.00017 | $0.01265 |
Grade C, and why
cos-setup scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "$BOARD_URL/api/addons" | node -e 'let s="";process.stdin.on("data",d=>s+=d).on("end",()=>{const a=JSON.parse(s).addons.find(x=>x.id==="nutrition");process.exit(a&&a.enabled===true?0:1)})' && echo "add-on enabled Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "$GUARD_SIDECAR_URL/healthz" How it starts
The opening of the file, as written. The whole thing — 592 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cos — full first-run setup (orchestrator)
This is the root runbook that brings the whole system up on a fresh machine. It does not re-implement the component skills — it sequences them in the one order that works, because each step produces what the next one needs: the vault must exist before the MCP can point at it and before backup has something to protect; the guard model must be configured before the guard bridge can report a real classifier; all the bridges + sidecars must be wired before backup can snapshot live, populated stores. Run the four sub-skills in order, stop at each CHECKPOINT, and only advance when it passes. End with the § End-to-end verification, then finish with Step 5 — operator automation, which is what makes the system run itself.
Every shell step below begins with the loader line
source "$(git rev-parse --show-toplevel)/config/load-config.sh", which exports $REPO_ROOT
(git-derived), $BREW_PREFIX, $LAUNCH_AGENTS_DIR, $COWORK_CONFIG, $VAULT_DIR, $BOARD_URL,
and the bridge/sidecar ports + URLs — use those instead of hardcoding paths, ports, or your
username. The only value still derived inline is $U=$(id -u), which launchctl needs at runtime.
Prerequisites checklist (gather these BEFORE step 1)
- node + npm (Homebrew) — bridges, vault Agent SDK, backup.
node -v. - supergateway —
npm install -g supergateway. The stdio→HTTP bridge for Claude Code. - uv (Homebrew:
brew install uv) — runs the two Python sidecars (search:8008, guard:8009); self-provisions each venv on first launch. - hf CLI (
pip install -U huggingface_hub/brew install huggingface-cli) + a Llama license — only if you want the real gated guard model (step 2). The heuristic-only fallback needs none of this. - ANTHROPIC_API_KEY (
sk-ant-…) inconfig/secrets.env— the vault bridge embeds the Agent SDK and makes outbound Anthropic calls; it is the only bridge that needs a key, and the key goes in this one gitignored file (the launch wrapper loads it), never in the plist. - A PRIVATE GitHub backup repo + a recovery passphrase — step 4. Encrypted, off-site.
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.
- 4d ago First seen · 592 lines · 167 tokens per session scan C eda5bfa65013
cos-setup is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed today), licensed MIT. It adds 167 tokens to every session and 12,654 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.
memory-curate
Curate the Basic Memory knowledge graph: find orphan notes and suggest links, propose typed relations, merge duplicates, audit tags and folders, and build hub notes. Use to organize, connect, and improve a knowledge base as notes accumulate.
memory-metadata-search
Structured metadata search for Basic Memory: query notes by custom frontmatter fields using equality, range, array, and nested filters. Use when finding notes by status, priority, confidence, or any custom YAML field rather than free-text content.
founder-voice
Founder voice enforcement for all written output. Apply to any text another person will read.
lint
Run deterministic integrity, provenance, projection, link, alias, operation, and secret checks over raytsystem. Use for LINT, health checks, pre-commit verification, stale projection diagnosis, broken evidence, or semantic review; never auto-fix canonical knowledge.
remem-plugin-version-sync
Keep remem binary, Cargo, Codex plugin, release manifest, and npm wrapper versions synchronized. Use when changing package.version, release metadata, plugin runtime behavior, npm wrapper behavior, or when CI/checkpluginversionsync.py or checkversionbump.py fails.