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 ribeirogab/zeno-agent --skill zeno-developmentgit clone --depth 1 https://github.com/ribeirogab/zeno-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/ribeirogab/zeno-agent/zeno-development)<a href="https://agentmods.dev/skills/ribeirogab/zeno-agent/zeno-development"><img src="https://agentmods.dev/badge/skills/ribeirogab/zeno-agent/zeno-development/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/ribeirogab/zeno-agent/zeno-development"><img src="https://agentmods.dev/badge/skills/ribeirogab/zeno-agent/zeno-development.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 | $0.00103 | $0.02325 |
| Opus 5.5 | $0.00041 | $0.00930 |
| Sonnet 5.5 | $0.00021 | $0.00465 |
| Haiku 4.5 | $0.00010 | $0.00232 |
Grade A, and why
zeno-development 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 2mo 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zeno Development
Structured git workflow for cloning repos and delivering code changes via PRs. Uses bare clones + worktrees so the main branch stays pristine and multiple tasks can run in parallel without stepping on each other.
This is a default Zeno skill — it ships with the agent and applies to any profile. Profile-specific skills (e.g. acme-code-review) layer on top of this baseline.
Prerequisites
This skill assumes:
- A
github-app-*connector is installed via the dashboard for the org you want to work in. The connector exposes the GitHub App tokens the operator wired up; without it,ghandgit pushwill fail with 401/403. - Capabilities
Bash,Read,Edit,Write,Glob,Grepare enabled in/settings/agent-capabilities(default-on for fresh installs). - The container has
/workspacemounted as a writable volume.
If any prerequisite is missing, stop, tell the operator clearly what's missing, and suggest the fix (e.g. "Install a GitHub App connector pointing at org-name").
Directory convention
/workspace/
└── <provider>/ # github, gitlab, bitbucket…
└── <owner>/ # org or user
├── <repo>.git/ # bare clone (git objects only)
└── <repo>/
├── main/ # worktree: default branch (READ-ONLY)
├── zeno/add-readme/ # worktree: active task
└── zeno/fix-login/ # worktree: another active task
Provider is extracted from the clone URL: github.com → github, gitlab.com → gitlab.
First clone of a repo
Run these steps when you encounter a repo for the first time (no .git/ directory exists at the expected path).
# Variables (set these first — replace with your own GitHub org / username)
PROVIDER="github"
OWNER="<your-github-username>"
REPO="my-app"
BARE="/workspace/${PROVIDER}/${OWNER}/${REPO}.git"
WORKTREES="/workspace/${PROVIDER}/${OWNER}/${REPO}"
# 1. Bare clone
gh repo clone "${OWNER}/${REPO}" -- --bare "${BARE}"
# 2. Fix fetch refspec (gh clone --bare doesn't set it correctly)
git -C "${BARE}" config remote.origin.fetch '+refs/heads/*:refs/remotes/origin/*'
# 3. Fetch all branches
git -C "${BARE}" fetch origin
# 4. Detect default branch
DEFAULT_BRANCH=$(git -C "${BARE}" remote show origin | grep 'HEAD branch' | awk '{print $NF}')
# 5. Create main worktree (read-only reference)
git -C "${BARE}" worktree add "${WORKTREES}/main" "${DEFAULT_BRANCH}"
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.
- 2mo ago First seen · 209 lines · 103 tokens per session scan A 9b4dd026c104
zeno-development is a skill published in the GitHub repository ribeirogab/zeno-agent (10 stars, last pushed 5mo ago), licensed MIT. It adds 103 tokens to every session and 2,325 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 2026-08-31.
Other skills, from other repositories
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
version-bump
Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. npm publishing is done by the tag-triggered GitHub Actions workflow through…
emerging-techniques-model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
release
Fully automate a release with version-bump and childhood.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.