Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cogni-work/insight-wave/plugin install cogni-workspaceWrote 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/cogni-work/insight-wave/manage-workspace)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/manage-workspace"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/manage-workspace/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/cogni-work/insight-wave/manage-workspace"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/manage-workspace.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 | $0.00169 | $0.04203 |
| Opus 5.5 | $0.00068 | $0.01681 |
| Sonnet 5.5 | $0.00034 | $0.00841 |
| Haiku 4.5 | $0.00017 | $0.00420 |
Grade A, and why
manage-workspace scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Required: `jq`, `python3`, `bash` 3.2+. If required dependencies are missing, show the user what to install before continuing. Optional dependencies (`curl`, `git`, `bc`) are fine to skip. How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Workspace
Why This Exists
An insight-wave workspace is the shared foundation that all marketplace plugins depend on. It centralizes environment configuration, theme storage, and plugin registration so that plugins can find each other and share resources. Without a workspace, plugins operate in isolation: they can't resolve each other's paths, and there is no shared place for user-created themes.
This skill handles both initial creation and ongoing updates. It auto-detects which mode to use based on whether a workspace already exists.
Before Starting
Run the dependency checker — it returns JSON, so parse the result and tell the user exactly what's missing:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/check-dependencies.sh
Required: jq, python3, bash 3.2+. If required dependencies are missing, show the user what to install before continuing. Optional dependencies (curl, git, bc) are fine to skip.
Detect Mode
Determine the workspace target path:
- User-provided path (if they specified one)
$PROJECT_AGENTS_OPS_ROOTenvironment variable- Current working directory
Check for .workspace-config.json at the target path:
- Not found → Init mode (section below)
- Found → Update mode (section further below)
Init Mode
Use this flow when no workspace exists yet at the target path.
1. Discover Plugins
Scan the marketplace cache for installed cogni-* plugins:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/discover-plugins.sh
The script returns JSON with each plugin's name, version, path, and computed environment variable names. Present the list to the user so they can confirm, add, or remove plugins before proceeding. This matters because the plugin list determines which environment variables get generated — missing a plugin here means it won't be wired up.
2. Gather Preferences
Use AskUserQuestion to collect:
- Language — EN or DE. This is written as the
languagekey by step 3, which Claude Code turns into a# Languagesystem-prompt section, so a fresh session responds in the workspace language. Bilingual plugins read the same value as their default. - Plugin confirmation — Show discovered plugins, let the user adjust.
- Tool integrations — Obsidian, VS Code, other. This gets stored in the config so tool-specific plugins know what to set up later.
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 First seen · 345 lines · 169 tokens per session scan A 453f167b9ff5
manage-workspace is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 169 tokens to every session and 4,203 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…