Borrowing it
Nothing to install: this file belongs to jstoup111/ai-conductor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jstoup111/ai-conductor/main/.agents/skills/release-disposition/SKILL.mdgit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/release-disposition)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/release-disposition"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/release-disposition/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/jstoup111/ai-conductor/release-disposition"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/release-disposition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.01231 |
| Opus 5.5 | $0.00011 | $0.00492 |
| Sonnet 5.5 | $0.00005 | $0.00246 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
release-disposition 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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Disposition
Write the authoritative release disposition for this repository's retained SHIP draft PR.
Shared outcome
This repository-local pre-finish gate judges the implementation diff, not the draft placeholder.
It writes exactly one valid structured release disposition directly into the retained draft PR body.
The PR body is authoritative; .pipeline/release-disposition-pass is evidence only. The later
finish step writes reader-facing PR content while preserving this metadata block.
The selected host uses its authenticated repository PR interface to read and update the retained
draft PR. Claude Code invokes this skill as /release-disposition; Codex invokes it as
$release-disposition. If the retained draft cannot be resolved or updated, return BLOCKED.
Procedure
- Remove
.pipeline/release-disposition-passbefore judging the diff. Overwrite.pipeline/release-disposition-review.mdat the start; never append prior evidence. - Read the retained SHIP draft PR body and the feature diff against its base. Inspect code, tests, configuration, hook wiring, skill symlinks, and CLI changes as applicable. The diff is authority; the placeholder and prior metadata are not a disposition decision.
- Record exactly one
Surface-Verdict:line in.pipeline/release-disposition-review.md. Its value is one ofnone|migration|waiver|unclassifiable. Classify breaking surfaces using the release gate's canonical names:bin/conduct CLI,skill symlink targets,hook wiring, andsettings.json schema. RecordSurface-Verdict: nonewhen the diff has no classified breaking surface; it authors no waiver and no migration block. When the diff has a classified breaking surface and no waiver committed in the feature diff, and you cannot confidently judge whether the change is internal-only or consumer-facing, recordSurface-Verdict: unclassifiable; do not guesswaiverormigration. - Write only inside the
<!-- ai-conductor:step release-disposition -->…<!-- /ai-conductor:step -->region. Replace itsRelease-Disposition,Release-Category,Release-Semver,Release-Note, and## Migrationmetadata while leaving both region markers and all content outside the region unchanged. - Write one of these valid forms directly to the retained draft PR body:
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.
- 1mo ago Changed · +2 lines 1b6334e1ca2d
- 1mo ago Changed · +2 lines adbb013e8888
- 1mo ago Changed · +29 lines 61b587a93734
- 2mo ago First seen · 62 lines · 27 tokens per session scan A 3287105a579a
release-disposition is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 1,231 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
release
Fully automate a release with version-bump and childhood.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.