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/opencoven/coven/coven-parallel-worknpx skills add OpenCoven/coven --skill coven-parallel-workgit clone --depth 1 https://github.com/OpenCoven/covenWrote 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/opencoven/coven/coven-parallel-work)<a href="https://agentmods.dev/skills/opencoven/coven/coven-parallel-work"><img src="https://agentmods.dev/badge/skills/opencoven/coven/coven-parallel-work.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 5.1 | $0.00068 | $0.02013 |
| Opus 5 | $0.00034 | $0.01007 |
| Sonnet 5 | $0.00014 | $0.00403 |
| Haiku 4.5 | $0.00007 | $0.00201 |
Grade A, and why
coven-parallel-work 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 6d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coven Parallel Work Protocol — OpenClaw entry point
What this is
The Coven Parallel Work Protocol is a portable, harness-agnostic
contract for safely running multiple agents on the same git repo on the
same machine. It works for Codex, Claude Code, OpenClaw, Hermes, Nova,
and any future runtime — anyone who runs git.
This skill file is the OpenClaw familiar's entry point: it tells you when to use the protocol from inside an OpenClaw session, the local prototype tooling available, and the daily workflow.
For the full spec (harness-agnostic, no OpenClaw assumptions), read
PROTOCOL.md — that's the contract any conforming
implementation must respect.
Where this lives
- Spec:
PROTOCOL.md(in this directory; portable, will move upstream) - Reference prototype: POSIX-shell scripts in
~/.openclaw/workspace/bin/cv-wt,cv-claimand hook templates in this directory'shooks/ - Canonical implementation (target):
OpenCoven/coven— surfaced eventually ascoven wt,coven claim,coven hooks install. Not yet built. Tracked upstream in issue #167. - This skill: how an OpenClaw familiar uses the protocol day-to-day
The local prototype is intentionally a prototype. It's working code that respects the spec, sized to fit one user's setup. Once the canonical Coven implementation lands, this skill will redirect to it and the prototype scripts will become a thin shim or get retired.
When to apply
Use the protocol when:
- A repo is touched by 2+ concurrent agents (or agent + human, or long-lived background bots like release-bumpers).
- You've seen any of: HEAD reset out from under you, stash auto-applied
someone else's WIP, force-push collisions, a bot direct-merging to
mainmid-PR, untracked files leaking between sessions. - A new Coven user is setting up shared agents on one workspace.
If only one agent ever touches a repo, you don't need the protocol. Don't over-apply.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 215 lines · 68 tokens per session scan A c58c18a013a6
coven-parallel-work is a skill published in the GitHub repository OpenCoven/coven (46 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 2,013 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
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
ppt-review
Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.
package-installer
Install third-party open-source projects (a GitHub URL or a local git directory the user provides) as external packages. The project is cloned verbatim into the per-user packages directory — never edit, normalize, or reorganize its files.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
helmor-debug-operate
Operate, reproduce, and debug a running local Helmor desktop development build through the Tauri MCP bridge. Use when the user asks to use Tauri MCP, towery MCP, the local dev build, the Tauri webview, visual end-to-end validation, UI automation, screenshots, DOM/accessibility snapshots, IPC or log tracing…
review
5-pass structured code review — correctness, security, performance, readability, consistency.