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 wahidyankf/ose-public --skill repo-practicing-trunk-based-developmentgit clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/repo-practicing-trunk-based-development)<a href="https://agentmods.dev/skills/wahidyankf/ose-public/repo-practicing-trunk-based-development"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/repo-practicing-trunk-based-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/wahidyankf/ose-public/repo-practicing-trunk-based-development"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/repo-practicing-trunk-based-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 | $0.00128 | $0.00963 |
| Opus 5.5 | $0.00051 | $0.00385 |
| Sonnet 5.5 | $0.00026 | $0.00193 |
| Haiku 4.5 | $0.00013 | $0.00096 |
Grade A, and why
repo-practicing-trunk-based-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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trunk Based Development Skill
Purpose
This Skill provides comprehensive guidance on Trunk Based Development (TBD) - the git workflow used throughout this repository: small, frequent commits integrated continuously into main through short-lived, single-purpose branches. The default delivery mode is worktree-to-pr; direct commit to main has no executable path in ose-public (branch-protected).
When to use this Skill:
- Planning git workflow, deciding whether to create a branch
- Managing incomplete work via feature flags
- Navigating environment branches (deployment only)
- Creating plans with git workflow specs; implementing AI agent default behaviours
PRs follow natural cohesive seams, never numeric LOC or file-count boundaries. Keep every artifact
needed for internal consistency together, merge only an immediately production-deployable resulting
main state, and integrate each ready unit promptly. Incomplete behaviour must be
complete-and-inert behind a temporary production-disabled flag, with both paths tested and rollout,
rollback, and removal recorded.
Core Concepts
See Core Concepts for what TBD requires (convergence on main, short-lived branches, feature flags) and why.
Delivery Modes: How Work Reaches main
See Delivery Modes: Default Behaviour for the standard worktree-to-pr workflow, and Delivery Modes: Direct Push for why no direct-push mode is available.
Keeping Branches Short-Lived
See Keeping Branches Short-Lived for what TBD actually forbids, the four legitimate longer-lived categories, and reasons that do NOT justify a branch outliving its plan.
Feature Flags for Incomplete Work
See Feature Flags for the basic pattern, the four-phase lifecycle, and DO/DON'T guidance.
Environment Branches and AI Agent Default Behaviour
What ships with it
12 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.
- README.md 912 B
- reference/commit-patterns.md 2.3 KB
- reference/common-mistakes-and-best-practices.md 2.8 KB
- reference/common-patterns.md 3.0 KB
- reference/core-concepts.md 1.9 KB
- reference/delivery-modes-default-behaviour.md 1.9 KB
- reference/delivery-modes-direct-push.md 810 B
- reference/environment-branches-and-ai-agent-behaviour.md 2.9 KB
- reference/feature-flags.md 2.1 KB
- reference/keeping-branches-short-lived.md 3.6 KB
- reference/pr-default-and-direct-push.md 2.0 KB
- reference/README.md 1.2 KB
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.
- 2d ago First seen · 80 lines · 128 tokens per session scan A 83bdef36edc8
repo-practicing-trunk-based-development is a skill published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 128 tokens to every session and 963 once invoked, about $0.0005 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 2026-10-14.
Other skills, from other repositories
upgrade-packages-js
Safely upgrade JavaScript packages with breaking change detection, migration guidance, and automated code migrations (npm/pnpm/yarn). Cross-platform with git safety branch enforcement.
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
commit
Commit staged or unstaged changes with an AI-generated commit message that matches the repository's existing commit style. Use when the user asks to 'commit', 'commit changes', 'create a commit', 'save my work', or 'check in code'.
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
review-triage-phase
Produces canonical review actions from fetched review state and renders action markdown. Use when the user wants only triage/action-planning for the review-framework workflow.
multiline-commit-messages
Use single-quoted strings for multiline git commit messages in the Shell tool. Prevents heredoc escaping failures that produce garbled commit messages.