What is workspace-knowledge?

A read-only workspace question-answering workflow for projects split across multiple repositories. It uses an ownership index to identify which repository handles a feature, endpoint, event, or other concern, then routes the question for detail.

Use it to answer questions such as which repository owns login, where a database record is written, or which services emit an event.

It avoids searching every repository manually when you need to find where a responsibility lives. It also separates high-level ownership from repository-specific explanations.

workspace-knowledge — Skill for Claude Code and Codex by architonixlabs: A read-only workspace question-answering workflow for projects spli

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/architonixlabs/repoorch/workspace-knowledge

Any agent

npx skills add architonixlabs/RepoOrch --skill workspace-knowledge

Clone the repo

git clone --depth 1 https://github.com/architonixlabs/RepoOrch

Made for: Claude Code, Codex.

Or install repo-orchestrator, the plugin that ships this one along with the rest of its 3 skills, 8 commands, 2 agents, 2 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/architonixlabs/repoorch/workspace-knowledge.svg)](https://agentmods.dev/skills/architonixlabs/repoorch/workspace-knowledge)

Your own site

<a href="https://agentmods.dev/skills/architonixlabs/repoorch/workspace-knowledge"><img src="https://agentmods.dev/badge/skills/architonixlabs/repoorch/workspace-knowledge.svg" alt="Measured on agentmods" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,463 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.

Model	Per session	Once invoked
Fable 5.1	$0.00091	$0.01463
Opus 5	$0.00046	$0.00732
Sonnet 5	$0.00018	$0.00293
Haiku 4.5	$0.00009	$0.00146

Measured 5d ago against content hash 5c05f1218bc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

workspace-knowledge 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 5d 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.

skills/workspace-knowledge/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Knowledge Skill (Master Tier)

Use this skill when a developer, architect, or designer asks a knowledge question about the workspace rather than a single, already-known repo — e.g. "which repo handles login?", "where does the user table get written?", "what services emit order.created?", "how does auth flow across repos?".

This is the master tier of the two-tier knowledge model:

Master (this skill) holds only the ownership index — which repo is responsible for what — and redirects to the owning repo. It does not hold per-repo detail.
Per-repo (the repo-<name> specialist agent + its context file / graph) holds the deep detail. The master hands off to it.

Distinction from the routing skill: routing selects specialists for a ticket/incident in a triage flow. workspace-knowledge answers a question and returns an explanation, routing to the owning repo(s) and synthesizing — not spinning up a triage team.

This skill is read-only and needs no API key: it reads local registry.json and repo context, and delegates to existing agents.

Step 1 — Load the ownership index

Read .repo-orchestrator/registry.json. If it does not exist, stop:

"Registry not found. Run /repo-orch-init first."

The registry is the master's entire knowledge: one entry per repo with name, path, owns, endpoints, emits, consumes, dependsOn, providesTo, and the contract fields. The per-repo detail lives in .repo-orchestrator/context/<name>.md and the Claude-native knowledge summary .repo-orchestrator/graphs/<name>/summary.json (built by /repo-orch-graph) — the master only indexes and redirects.

Step 2 — Classify the question

Single-repo — the question names a repo, or one repo is the obvious owner. → Hand off to that one specialist (Step 4).
Which-repo / where-is — "which repo owns X?", "where does X live?". → Score and return the owner(s) (Step 3 → 4).
Cross-repo — spans multiple services ("how does auth flow from gateway to payments?", "what breaks if I rename userId?"). → Resolve all involved repos and synthesize across their handoffs (Step 4, multiple).

Read the full file on GitHub · 76 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.

5d ago First seen · 76 lines · 91 tokens per session scan A 5c05f1218bc8

Subscribe to this mod's changes

workspace-knowledge is a skill published in the GitHub repository architonixlabs/RepoOrch (3 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 1,463 once invoked, about $0.0005 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.

Productivity agent-teams ai-agents claude-code claude-code-plugin devtools microservices

temporal

Help developers use Temporal for durable execution workflows. Covers CLI commands, SDK patterns (Go, TypeScript, Python, Java), workflow orchestration, and architectural decisions.

rube-de/cc-skills · 36 tokens

automation-refactor

Expert automation workflow refactoring tool for Power Automate, n8n, Make, Zapier and other platforms. Optimizes existing flows by improving performance, reliability, maintainability, and best practices compliance. Triggers when user wants to improve, optimize, refactor, correct values, enhance, or modernize…

MacroMan5/AutomationHelper_plugins · 88 tokens

release-notes

Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.

kenryu42/cc-safety-net · 65 tokens

workspace-knowledge