objectstack-pm-dispatch

A project-management workflow that selects GitHub issues, sends them to separate coding agents, reviews their reports and changes, and moves accepted pull requests toward completion. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
Use it to triage ready GitHub issues, assign work to parallel developer agents, collect structured results, check the changes against project rules, review pull requests, and produce progress reports.
Why use it?
It reduces the manual coordination needed to process a backlog of development tasks. The maintainer mainly handles decisions that genuinely require human judgment.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/objectstack-ai/objectstack/objectstack-pm-dispatch
Any agent
npx skills add objectstack-ai/objectstack --skill objectstack-pm-dispatch
Clone the repo
git clone --depth 1 https://github.com/objectstack-ai/objectstack

Made for: Claude Code, Codex.

Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00201 $0.13302
Opus 5 $0.00101 $0.06651
Sonnet 5 $0.00040 $0.02660
Haiku 4.5 $0.00020 $0.01330

Measured yesterday against content hash df06adc6be49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

objectstack-pm-dispatch 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 yesterday.

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.

skills/objectstack-pm-dispatch/SKILL.md · 1,070 lines

How it starts

The opening of the file, as written. The whole thing — 1,070 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM dispatch — a multi-agent delivery loop for any project

This skill turns one session into a PM agent: it never writes code itself. It selects work from a GitHub backlog and hands each issue to a developer agent that returns a structured report, then reviews and lands the result.

select → claim → dispatch → collect → review → report → next batch

The maintainer stays out of the loop except at two points: the round report printed after each batch, and the decision issues filed when something genuinely needs a human call.

Nothing in this skill is specific to one codebase. Everything project-specific — gates, release-note artifacts, branch naming, review requirements — is read from your project's own conventions file (AGENTS.md, CLAUDE.md, CONTRIBUTING.md, …). When this skill and that file disagree, the project's file wins.


Quickstart

1. Install

npx skills add objectstack-ai/objectstack/skills --skill objectstack-pm-dispatch

(Installing the whole ObjectStack bundle with --all includes it.)

2. Configure — optional. With no config the loop runs against the current repository: it is the only shard and the backlog. Add .claude/pm-dispatch.json only when you have more than one repository, a separate backlog repository, or want different defaults.

3. Run

/pm-dispatch                 # drain the pm:queue backlog, 3 agents at a time
/pm-dispatch batch:5         # wider batch
/pm-dispatch #<n> #<n>       # two named issues, nothing else
/pm-dispatch rounds:1        # one round, then stop and report

The first round creates the labels it needs (idempotent), sweeps the backlog, and prints a round report when the batch is done.


Configuration

The loop reads .claude/pm-dispatch.json from the repository the session starts in. The file is optional. Every key has a default that makes a single-repository project work with no configuration at all.

{
  "backlogRepo": "acme/hotcrm",
  "repos": ["acme/hotcrm", "acme/hotcrm-web"],
  "batch": 3,
  "mode": "subagent",
  "conventionsFile": "AGENTS.md",
  "routingLabelPrefix": "repo:"
}

Read the full file on GitHub · 1,070 lines

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. yesterday First seen · 1,070 lines · 201 tokens per session scan A df06adc6be49

Subscribe to this mod's changes

objectstack-pm-dispatch is a skill published in the GitHub repository objectstack-ai/objectstack (45 stars, last pushed yesterday), licensed Apache-2.0. It adds 201 tokens to every session and 13,302 once invoked, about $0.0010 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 2026-08-30.

Related

Other skills, from other repositories

ontotect

Systematic ontology engineering for designing, constructing, reviewing, repairing, optimizing, refactoring, validating, documenting, and governing ontologies, vocabularies, taxonomies, knowledge graphs, semantic models, and mappings. Use for RDF/RDFS, OWL 2, SKOS, SHACL, SPARQL, OBO, Turtle, JSON-LD, RDF/XML…

Moonweave-AI/Ontotect · 152 tokens

mykg

Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs it, and…

SenolIsci/mykg · 173 tokens

mykg-github-pages

Set up and maintain the GitHub Pages site for the mykg repo (SenolIsci/mykg) — a purpose-built pages/ folder (landing page adapted from README.md, blog posts, diagrams), built by a GitHub Actions workflow that runs Jekyll and deploys the result to a gh-pages branch. Use whenever the user wants to publish project…

SenolIsci/mykg · 228 tokens

networkx

Build, analyze, and visualize networks and graphs using NetworkX (Python). Use this skill whenever the user wants to: create graphs or networks, analyze graph properties, compute centrality measures, find shortest paths, detect communities, run graph algorithms, convert graphs to/from matrices or dataframes, visualize…

SenolIsci/mykg · 163 tokens

design-architecture

Reviews the current codebase architecture and proposes improvements using four parallel specialist subagents: System Architect, Software Architect, Data Architect, and an Adversarial Architect that red-teams failure paths, LLM adversarial output scenarios, silent corruption risks, and invariant bypasses. Each subagent…

SenolIsci/mykg · 195 tokens

exchange-recovery

Accident Request (用户输入事故请求) ↓ Think (分析事故 → 决策恢复策略) ↓ Risk Evaluate (评估数据覆盖风险) ↓ Plan (列出Exchange服务器 → 查找备份时间点 → 浏览备份邮件 → 生成恢复任务) ↓ Act (执行恢复任务 → 产生恢复作业 → 验证Exchange可用性) ↓ Report (生成恢复报告:状态 + 数据统计 + 时效评估).

openbkn-ai/bkn-foundry · 0 tokens