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/openclaw-devnpx skills add OpenCoven/coven --skill openclaw-devgit clone --depth 1 https://github.com/OpenCoven/covenWhat 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 | $0.00042 | $0.01230 |
| Opus 5 | $0.00021 | $0.00615 |
| Sonnet 5 | $0.00008 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
openclaw-dev 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 2d 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.
curl -sL https://docs.openclaw.ai/llms-full.txt -o ~/.openclaw/workspace/cache/openclaw-docs.txt How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw Dev Agent
A docs-aware development agent for the OpenClaw ecosystem. This skill is
OpenClaw-only. For OpenCoven/coven PR creation, use skills/pr-agent, the Coven PR Readiness Agent.
Capabilities
1. PR Workflow (from openclaw/maintainers)
Three-phase maintainer workflow with strict quality gates:
/review-pr <PR>— Read-only review, structured findings, recommendation/prepare-pr <PR>— Rebase, fix findings, run gates, push to PR head/merge-pr <PR>— Squash-merge with attribution, verify MERGED state
Source of truth: openclaw/maintainers/.agents/skills/PR_WORKFLOW.md
2. Docs-Aware Development
Fetches and caches OpenClaw documentation for context-grounded answers:
# Cache docs locally (run periodically)
curl -sL https://docs.openclaw.ai/llms-full.txt -o ~/.openclaw/workspace/cache/openclaw-docs.txt
The agent loads relevant doc sections per task, avoiding full 2MB context on every spawn.
3. Issue Triage
Classify and route incoming issues:
- Bug: Reproduction steps, affected version, severity estimate
- Feature: Design impact, scope estimate, suggested milestone
- Docs: Which page needs updating, draft content
- Security: MITRE ATLAS classification, severity, disclosure handling
4. Release Prep
- Changelog generation from merged PRs
- Version bumping (semver)
- Tag creation and release notes
- Clawtributor list update
5. Architecture Review
- "Should this be a plugin or core?" decisions grounded in docs
- Config schema validation against documented options
- Channel/tool API compliance checking
- Cross-repo impact analysis (openclaw, maintainers, lobster, docs)
Docs Loading Strategy
Priority chain:
- Local cache:
~/.openclaw/workspace/cache/openclaw-docs.txt - Web fetch:
https://docs.openclaw.ai/llms-full.txt - Local docs dir:
~/.nvm/versions/node/*/lib/node_modules/openclaw/docs/
Refresh: Cache is refreshed when stale (>24h) during heartbeat or on first use.
What ships with it
1 file 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.
- 2d ago First seen · 153 lines · 42 tokens per session scan A 8392db905515
openclaw-dev is a skill published in the GitHub repository OpenCoven/coven (41 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,230 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
github
GitHub workflow — creating and managing repos, always working on feature/development branches (never committing core changes directly to main), PR conventions, branch protection, and gh CLI patterns.
github-cli
Automate GitHub workflows using the gh CLI for pull requests, issues, releases, actions, and repository management. Use when interacting with GitHub beyond basic git operations.
pr-triage
PR triage: audit open PRs, deep review selected ones, draft and post review comments. Args: "all" to review all, PR numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
pr
Use when reviewing an incoming GitHub pull request — runs the multi-level (L1-L5) audit against the PR's real diff range, posts findings as one batched review (inline, summary, or local-only), offers the standard fix chain on NEEDSFIX, and optionally merges. The maintainer-side counterpart to /hyperflow:issue. Trigger…
workflow-creator
Compose durable multi-step workflows with the workflowcreate tool — step shape, agent binding, required skills, and the validation errors worth avoiding.
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries.