CUGA is an enterprise agent harness that turns business requests into actions across applications, APIs, and documents while connecting to tools through MCP, OpenAPI, and Python integrations. Organizations use it to run general-purpose agents in controlled environments, apply approval and execution policies, and configure models and workflows for private or disconnected deployments. The catalogue entries supply instructions and skills for working with the CUGA harness.
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 cuga-project/cuga-agent --skill cuga-github-issuesgit clone --depth 1 https://github.com/cuga-project/cuga-agentWrote 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/cuga-project/cuga-agent/cuga-github-issues)<a href="https://agentmods.dev/skills/cuga-project/cuga-agent/cuga-github-issues"><img src="https://agentmods.dev/badge/skills/cuga-project/cuga-agent/cuga-github-issues/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/cuga-project/cuga-agent/cuga-github-issues"><img src="https://agentmods.dev/badge/skills/cuga-project/cuga-agent/cuga-github-issues.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 | $0.00088 | $0.01235 |
| Opus 5.5 | $0.00035 | $0.00494 |
| Sonnet 5.5 | $0.00018 | $0.00247 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
cuga-github-issues 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 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.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CUGA GitHub issues
File issues against origin upstream with gh. Read companions as needed:
- github_commands.md — list/link/verify recipes
- templates.md — body sections and title prefixes
Shared rules
- Use upstream
origin(not a fork-only default). Pass--repo owner/namewhen needed. - Run
gh label listfor that repo. Only use label names that exist. Never invent labels. - No promotional footers (“Made with Cursor”, etc.).
- Hierarchy depth is only: Epic → Feature → Issue. Never nest under a leaf issue. Never Feature → Feature. Never deeper than three levels.
- When parented: put
Part of #<number>.at the top of the body, create the issue, then link with GraphQLaddSubIssue. Body text alone is not enough. Verify parent afterward. - Do not use unsupported
gh issue edit --set-parent.
Detect intent
| User intent | Branch |
|---|---|
| Epic / large workstream | Create epic |
| Feature, design, refactor, perf, security, docs, test, chore, question | Create feature-family |
| Bug / unexpected behavior | Create bug |
| Leaf task under an existing feature | Create leaf under feature |
If unclear, ask once which kind they want.
Hierarchy placement
Find epics
List open epics (type: epic and titles with [Epic] / [EPIC]). See github_commands.md.
Find features under an epic
List sub-issues of the candidate epic; prefer children whose titles start with [Feature] (or other feature-family prefixes) when attaching a leaf.
Match rules
- 0 matches: Tell the user none fit. Ask them to name an existing parent or create one first. Do not invent a parent.
- 1 clear match: Confirm number + title, then proceed.
- 2+ matches: Present
#N — titlewith one-line why each might fit. Do not pick for the user.
Create epic
- No parent search.
- Title:
[Epic] …(or[Epic]: …if matching existing style in the repo). - Labels: include
type: epicplus other applicable existing labels. - Prefer REST create with
type=Epic(see companion). - Body: summary of the workstream and what child features will cover. Use feature-request sections where useful (templates.md).
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.
- 1mo ago First seen · 106 lines · 88 tokens per session scan A d79975033e6c
cuga-github-issues is a skill published in the GitHub repository cuga-project/cuga-agent (1,007 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 1,235 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
pi-review-gated-delivery
Use when coordinating review-gated delivery of discrete GitHub issues between one implementation peer and a review-only lead, with user-owned Changesets and approval-gated commits.
gitlab
Read and manage GitLab projects, issues, merge requests, and pipelines via the GitLab REST API. Use when the user asks about GitLab projects, issues, MRs, or pipelines.
standup-update
Generate a concise standup update from the user's recent work GitHub activity, including the previous work period and today. Use when the user asks what they worked on, requests a standup update, or invokes /standup.
github-issues
Use gh CLI to view, triage, fix, link, create, or close GitHub Issues.