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 skills add arbiterForge/codeArbiter --skill releasegit clone --depth 1 https://github.com/arbiterForge/codeArbiterWrote 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/arbiterforge/codearbiter/release)<a href="https://agentmods.dev/skills/arbiterforge/codearbiter/release"><img src="https://agentmods.dev/badge/skills/arbiterforge/codearbiter/release/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/arbiterforge/codearbiter/release"><img src="https://agentmods.dev/badge/skills/arbiterforge/codearbiter/release.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.32652 |
| Opus 5.5 | $0.00010 | $0.13061 |
| Sonnet 5.5 | $0.00005 | $0.06530 |
| Haiku 4.5 | $0.00003 | $0.03265 |
Grade C, and why
release scanned grade C with 2 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
6. **Clean up declared-asset scratch state only after publication and the provenance snapshot succeed.** When assets were declared and steps 1 through 5 have passed through remote-ref capture, remove only the positively Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**This now extends to a Windows-hosted `pre-tag` row too (#602, closing the gap measured when the paragraph above was first written).** `run-pre-tag` resolves a POSIX-compatible shell (Git for Windows' own `bash.exe`, fo The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- today Changed 24503b6688fa
- 9d ago Changed f83d3cd76d14
- 29d ago Changed · +1 lines · -109 tokens per session 41f0ba04d419
- 1mo ago Changed · +150 lines b058a1cb97f5
- 1mo ago Changed · +63 lines 519ce462733e
- 1mo ago Changed · +49 lines 8cedbdc79404
- 1mo ago Changed · +7 lines 53bce304da82
- 1mo ago Changed · +50 lines · -1 tokens per session scan A → C bf925cb2edec
- 1mo ago First seen · 316 lines · 136 tokens per session scan A 10349019e300
release is a skill published in the GitHub repository arbiterForge/codeArbiter (149 stars, last pushed today), licensed AGPL-3.0. It adds 26 tokens to every session and 32,652 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
enterprise-harness
Use when enterprise work has been built and reviewed and needs a final mechanical ship or release gate before merge, PR readiness, install, deploy, or signoff. Checks proof trace, current diff, architecture, post-merge test kit, rollback, observability, security/privacy, and performance regression readiness.
promote
Promote dev to production (dev→main PR → gates → merge → migrations-first → pinned API deploy → portal verify → canary watch). Use when the user says "promote", "ship to main/prod", or "deploy the changes to main".
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
finishing-a-development-branch
A process for finishing a completed development branch. A branch is a separate line of code changes that can later be merged or submitted as a pull request.
goal-release
Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the Homebrew formula from the published release assets. Use when the user wants to draft and merge a release in one go, or…
writing-modpack-changelog
Use when cutting a modpack release. Creates /docs/release-changelog.md if absent; appends a new version section with grouped changes. Triggers - 'cut a release', 'release notes', 'changelog', 'v1.2.3 changes', 'what changed since last version'.