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/re-cinq/wave/gh-clinpx skills add re-cinq/wave --skill gh-cligit clone --depth 1 https://github.com/re-cinq/waveWhat 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 | $0.00045 | $0.00763 |
| Opus 5 | $0.00023 | $0.00381 |
| Sonnet 5 | $0.00009 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
gh-cli 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 yesterday.
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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub CLI (gh)
Work seamlessly with GitHub from the command line. For the complete command reference see references/full-reference.md.
Authentication
# Interactive login
gh auth login
# Login with token
gh auth login --with-token < token.txt
# Check status
gh auth status
# Switch accounts
gh auth switch --hostname github.com --user username
# Setup git credential helper
gh auth setup-git
# Print active token
gh auth token
Pull Requests
# Create PR (interactive)
gh pr create
# Create with title, body, base, draft, reviewer
gh pr create --title "Feature: X" --body "Details..." --base main --draft --reviewer alice
# List open PRs
gh pr list
# List with filters
gh pr list --author @me --labels bug --state all --limit 50
# View a PR
gh pr view 123
gh pr view 123 --comments --web
# Merge a PR
gh pr merge 123 --squash --delete-branch
# Check CI status
gh pr checks 123
gh pr checks 123 --watch
Issues
# Create issue (interactive)
gh issue create
# Create with title and labels
gh issue create --title "Bug: X" --body "Steps..." --labels bug,high-priority --assignee @me
# List open issues
gh issue list
# List with filters
gh issue list --assignee @me --labels bug --state all --search "is:open label:bug"
# View an issue
gh issue view 123
gh issue view 123 --comments --web
# Close / reopen
gh issue close 123 --comment "Fixed in PR #456"
gh issue reopen 123
Common Flags
| Flag | Description |
|---|---|
--repo OWNER/REPO |
Target a specific repository |
--json FIELDS |
Output JSON for given fields |
--jq EXPRESSION |
Filter JSON output with jq |
--web |
Open result in browser |
--paginate |
Follow pagination for large result sets |
--limit N |
Cap result count |
API Requests
# REST GET
gh api /user --jq '.login'
# REST POST with fields
gh api --method POST /repos/owner/repo/issues \
--field title="Issue title" --field body="Body"
# Paginate all results
gh api /user/repos --paginate
# GraphQL query
gh api graphql -f query='{ viewer { login } }'
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.
- yesterday First seen · 130 lines · 45 tokens per session scan A 7ca9f897306d
gh-cli is a skill published in the GitHub repository re-cinq/wave (20 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 763 once invoked, about $0.0002 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
coordinate-agents
Route Codex-native multi-agent orchestration in a Git repository through a local-first, recoverable Agent Bus. Use for role-based planning, task execution, review, recovery, adapters, and human-gated release workflows. The plugin supports Codex CLI, Google Antigravity CLI, Claude, and other configured coding agents.…
coordinate-task
Run a Coordinate Agents Task from requirement clarification through planning, implementation, review, and the human release gate. Hide Agent Bus transport details behind the durable Task API.
coordinate-recover
Diagnose and safely resume Coordinate Agents Tasks after executable failure, non-zero exit, timeout, stale claim, processing message, or Implementer ERROR. Recovery is explicit and never an automatic retry loop.
coordinate-setup
Discover coding CLIs on the current computer and configure a Coordinate Agents implementation agent. Use for setup, executable checks, registered agents, user-level configuration, and project-over-user precedence.
coordinate-review
Review a Coordinate Agents implementation as the Codex Reviewer. Verify the real commit, diff, tests, validation evidence, and specification without modifying the Implementer's product code.
api-contracts
Enforce API contract governance, strict backward compatibility, schema validation, and standardized RFC 7807 error responses.