repository-manager-development-lifecycle

repository-manager-development-lifecycle is a skill for Codex from Knuckles-Team/repository-manager. It costs 176 tokens per session (2,497 once invoked), scanned A, original, MIT.

A controlled lifecycle for taking one repository change from planning through an isolated work area, checks, submission, review, landing, or cancellation. A repository manager is the tool surface that governs those steps.

In plain words
What is it for?
Use it to start a unit of work, maintain its session, check readiness, submit it to a merge queue, monitor the result, or abort it cleanly.
Why use it?
It keeps work away from shared checkouts and replaces ad-hoc shell commands and manual merging with tracked repository-manager actions.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to start a unit of work, maintain its session, check readiness, submit it to a merge queue, monitor the result, or abort it cleanly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/knuckles-team/repository-manager/repository-manager-development-lifecycle
Install

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.

Any agent
npx skills add Knuckles-Team/repository-manager --skill repository-manager-development-lifecycle
Clone the repo
git clone --depth 1 https://github.com/Knuckles-Team/repository-manager

Made for: Codex.

Wrote 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.

agentmods badge for repository-manager-development-lifecycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-development-lifecycle/github.svg)](https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-development-lifecycle)
Your own site
<a href="https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-development-lifecycle"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-development-lifecycle/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.

agentmods 80×15 button for repository-manager-development-lifecycle

Your own site · 80×15
<a href="https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-development-lifecycle"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-development-lifecycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00176 $0.02497
Opus 5 $0.00088 $0.01248
Sonnet 5 $0.00035 $0.00499
Haiku 4.5 $0.00018 $0.00250

Measured 8d ago against content hash 891b742980ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

repository-manager-development-lifecycle 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 8d 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.

repository_manager/skills/repository-manager-development-lifecycle/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Manager — Development Lifecycle

The governed entrypoint for one unit of work: one agent session or one person, taking one repository from "nothing started" to "landed", without ever touching a canonical checkout, a raw shell command, a shared cargo target, or a hand-merge.

This skill invents nothing. Every step below is a named action on an existing condensed tool (rm_lane, rm_worktree, rm_merge_queue, rm_concepts) — confirmed against repository_manager/mcp_tools/contracts.py, repository_manager/lane_doctor.py, and the CLI parser (repository_manager/cli_commands/parser.py) on main. Where the brief's lifecycle name (heartbeat) does not correspond to a callable action, this skill says so explicitly rather than inventing one — see step 3.

When to use

  • Start here for any change an agent will eventually land into a shared base.
  • You need the whole arc — open isolation, work safely, prove readiness, hand off, watch it land, or cleanly back out — not just one raw verb.

When NOT to use

  • Fan-out across many repositories or a whole wave of lanes → repository-manager-fleet-scale-operations.
  • Bulk clone/pull/push/commit across repos with no single lane around it → repository-manager-bulk-git-operations.
  • Content-addressed build/cache mechanics → repository-manager-build-coordination.
  • Candidate/generation certification detail beyond "is my branch ready" → repository-manager-candidate-certification.
  • Registering or dispatching to a remote worker host → repository-manager-worker-operations.
  • Reserving/materializing a concept id in detail beyond step 1 below → repository-manager-concept-coordination.
  • Workspace-wide version/release planning → repository-manager-workspace-release.
  • Raw worktree/merge-queue verbs with no lifecycle narrative → repository-manager-worktree-orchestration / repository-manager-merge-and-reconcile. Those skills document the same tools at the mechanism level; this one documents the sequence an implementation agent should actually run.

Read the full file on GitHub · 141 lines

Files

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.

Changes

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.

  1. 8d ago First seen · 141 lines · 176 tokens per session scan A 891b742980ad

Subscribe to this mod's changes

repository-manager-development-lifecycle is a skill published in the GitHub repository Knuckles-Team/repository-manager (2 stars, last pushed 11d ago), licensed MIT. It adds 176 tokens to every session and 2,497 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.

Related

Other skills, from other repositories