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 Knuckles-Team/repository-manager --skill repository-manager-workspace-releasegit clone --depth 1 https://github.com/Knuckles-Team/repository-managerWrote 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/knuckles-team/repository-manager/repository-manager-workspace-release)<a href="https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-workspace-release"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-workspace-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/knuckles-team/repository-manager/repository-manager-workspace-release"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-workspace-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 | $0.00185 | $0.02084 |
| Opus 5 | $0.00093 | $0.01042 |
| Sonnet 5 | $0.00037 | $0.00417 |
| Haiku 4.5 | $0.00018 | $0.00208 |
Grade A, and why
repository-manager-workspace-release 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 10d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Manager — Workspace Release
Releasing a workspace is validate → bump → push, phased over a topologically
ordered dependency graph declared in workspace.yml's maintenance config (lower
phase = more upstream; a change in phase N only ever cascades to phases >= N,
never backward — CONCEPT:RM-PHASE-START/CONCEPT:RM-BUMP). This skill is about
running that safely and previewing it before anything mutates, not about what
"valid" means per project (that is repository-manager-workspace-validation) or
how a push actually executes (repository-manager-bulk-git-operations).
When to use
- Preview which repos would bump/push before running anything (
dry_run). - Run the full validate → consented-bump → consented-push chain in one call.
- Bump versions across the dependency-ordered workspace on their own.
- Scaffold, template, save, or list the
workspace.ymlmanifest.
When NOT to use
- Per-project validation semantics (pre-commit + pytest pass/fail) →
repository-manager-workspace-validation. - The actual
rm_git phased_pushmechanics and bulk clone/pull/push →repository-manager-bulk-git-operations. - Candidate/generation certification for one branch landing →
repository-manager-candidate-certification.
Tools & actions
| Condensed tool | Actions relevant here |
|---|---|
rm_workspace |
maintain, maintain_status, list, list_branches, setup, template, save |
rm_projects |
validate, validate_status (the consented bump/push chain lives here — see below) |
CLI: repository-manager --maintain --bump {patch,minor,major} [--phase N] [--single-phase] [--no-auto-start] [--project <name>] [--dry-run] [--allow-pre-commit] [--config <path>], and separately --validate [--bump ...] [--push] for the validate-then-release chain, or --push alone for phased push
only.
DAG preview — see the plan before anything mutates
dry_run=true on rm_workspace(action="maintain", ...) walks the same
topologically-phased plan a real run would — same phase map, same auto_start
lowest-pending-phase logic — and reports what would bump/tag, without committing
or tagging anything:
rm_workspace(action="maintain", part="patch", dry_run=true)
auto_start (default true) begins the walk at the lowest phase that actually
has pending work rather than always phase/1, so an unchanged upstream phase
is skipped along with its inter-phase wait — but a change in any phase still
cascades to every phase >= N. Pass projects= to restrict the walk to specific
repo names (re-bumping ones a prior run skipped), or force=true to bump even with
no detected changes (auto_start then stands down and starts exactly at phase,
since explicit targeting deliberately bypasses change detection).
What ships with it
2 files 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.
- 10d ago First seen · 160 lines · 185 tokens per session scan A 3f00868b3161
repository-manager-workspace-release is a skill published in the GitHub repository Knuckles-Team/repository-manager (2 stars, last pushed 13d ago), licensed MIT. It adds 185 tokens to every session and 2,084 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
Release Notes Generator
Generate professional software release notes from a commit log: classify changes, write user-facing summaries, draft a publishable announcement, and assess release readiness. Use for release, changelog, version, and deploy requests.
plugin-publish
A release guide for publishing Zhin.js plugins to npm, the JavaScript package registry, and to the Zhin plugin marketplace. It covers package metadata, versioning, release checks, and submission requirements.
release-manager
A release-management tool for calculating semantic versions, generating changelogs and release notes, creating tags, and preparing releases. Semantic versioning uses version numbers to describe the scale of changes.
operating-github-cli
Default GitHub skill for the action agent. Use githubcli for any GitHub request — create/list/view/close issues and PRs, assign, labels, repos, releases, checks, github.com/owner/repo URLs, or gh api. Prefer over shellrun/!gh. Run these with githubcli in the current agent turn.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.