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 commands/cdknorow/coral/publishgit clone --depth 1 https://github.com/cdknorow/coralWrote 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/commands/cdknorow/coral/publish)<a href="https://agentmods.dev/commands/cdknorow/coral/publish"><img src="https://agentmods.dev/badge/commands/cdknorow/coral/publish.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 | $0.00000 | $0.00150 |
| Opus 5 | $0.00000 | $0.00075 |
| Sonnet 5 | $0.00000 | $0.00030 |
| Haiku 4.5 | $0.00000 | $0.00015 |
Grade A, and why
publish 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.
What it actually says
Publish a new release of Coral to PyPI. The user provides the version number as $ARGUMENTS (e.g. "2.2.0").
This command follows the release process defined in .claude/skills/release.md. Run /release $ARGUMENTS to execute the full workflow, which includes:
- Review commits since last release
- Update
CHANGELOG.mdwith categorized changes - Bump version in
pyproject.toml - Run tests
- Build and verify the package
- Commit the release
- Ask user for confirmation before publishing
- Tag, push, upload to PyPI, and create GitHub Release
- Clean up build artifacts
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 · 14 lines · 0 tokens per session scan A c4e4f5fbc75a
publish is a command published in the GitHub repository cdknorow/coral (33 stars, last pushed 8d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 150 tokens. 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 commands, from other repositories
release
Command "release" from sageox/ox, covering release workflow, step 1: pre-flight checks, verify on main branch, clean working directory, run the executable in-repo release gates and step 1b: external harness compatibility evidence.
ng-ship-review
Portable command prompt generated from skills/checking-release-readiness/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
ship
Deliver completed work with validation and documentation.
release
This document describes the standard release process for agtrace.
wtfp:update
Check for a newer compatible package or plugin release and install it only after approval.
release-check
Pre-release validation checklist. Run all steps in order, stop at first failure.