Borrowing it
Nothing to install: this file belongs to jayminwest/warren. 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/jayminwest/warren/main/.agents/skills/os-eco-dep-sync/SKILL.mdgit clone --depth 1 https://github.com/jayminwest/warrenWrote 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/jayminwest/warren/os-eco-dep-sync)<a href="https://agentmods.dev/skills/jayminwest/warren/os-eco-dep-sync"><img src="https://agentmods.dev/badge/skills/jayminwest/warren/os-eco-dep-sync/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/jayminwest/warren/os-eco-dep-sync"><img src="https://agentmods.dev/badge/skills/jayminwest/warren/os-eco-dep-sync.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 | $0.00069 | $0.01943 |
| Opus 5 | $0.00034 | $0.00971 |
| Sonnet 5 | $0.00014 | $0.00389 |
| Haiku 4.5 | $0.00007 | $0.00194 |
Grade A, and why
os-eco-dep-sync 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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
os-eco-dep-sync
Use this skill inside the warren repo when you need to confirm warren is running the newest published versions of the other os-eco tools and bump it if not. Warren is the only ecosystem consumer, and it tracks the rest of os-eco across two surfaces that must stay in lockstep:
- npm dependencies in
package.json(+bun.lock):@os-eco/burrow-cliand@os-eco/plot-cli. These are what warren builds and imports against — consumed as published registry packages, not links. - Global CLI pins in the
Dockerfilebun install -gblock: all six bundled CLIs —@os-eco/burrow-cli,@os-eco/plot-cli,@os-eco/canopy-cli,@os-eco/seeds-cli,@os-eco/mulch-cli,@os-eco/sapling-cli— that back warren's opt-in features at runtime.
"Latest" always means the published npm version (npm view ... version),
never the local sibling working tree.
The burrow double-pin invariant.
@os-eco/burrow-cli(andplot-cli) appears in both surfaces.Bun.spawnresolves./node_modules/.bin/burrowbefore PATH, so bumping only the Dockerfile is a silent no-op — the supervisor keeps running the lockfile copy. The two pins MUST be identical. SeeCLAUDE.md→ "Relationship to burrow".
Pre-flight
cd warren # this skill operates only on the warren repo
git status # MUST be clean before you start
command -v bun npm git gh # gh optional (only for the PR step)
If the tree is dirty, stop and let the user commit or stash first — this skill ends in a focused, reviewable commit and a noisy tree defeats that.
Read the current pins so you know the starting point:
grep '@os-eco/' package.json
grep '@os-eco/' Dockerfile
Procedure
1. Discover the latest published version of each tool
for t in burrow plot canopy seeds mulch sapling; do
printf '%-8s %s\n' "$t" "$(npm view @os-eco/$t-cli version)"
done
If inputs.package was given, restrict the loop to that one tool. Record each
latest. Compare against the pins printed in pre-flight; anything behind is a
bump target. If every surface already matches latest, report "warren is
up to date" and stop — do not create an empty commit.
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 First seen · 171 lines · 69 tokens per session scan A ba9e86f4fb7b
os-eco-dep-sync is a skill published in the GitHub repository jayminwest/warren (387 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,943 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
factory-handoff
Hand one exact agent-ready ticket to the central Factory runtime over the configured SSH forced-command boundary. Use when an operator asks to hand off an existing ticket or a prose request instead of implementing it in the current session.
ticket-spec
Turn a raw Linear Triage ticket into a fully specified ai:agent-ready one by exploring the codebase. Use when specifying, refining, or promoting tickets, or when asked why a ticket isn't dispatchable.
create-coordclaw-team
A Skill for creating a CoordClaw multi-agent collaborative team. Through an 8-step standardized process, from requirement gathering to team validation, rapidly build a complete AI team.
write-file
Replaces OpenClaw built-in write tool for all plain text writing, providing.
ritual
Discover recurring behaviors from memory and offer to formalize them as scheduled jobs.
question-answering
General-purpose question answering capability powered by OpenRouter. Access 300+ LLM models (GPT-4o, Claude, Llama, Gemini, Mistral, etc.) through a single unified API. Handles conversational queries, explanations, code generation, analysis, and creative writing.