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 agentmods add skills/jandedobbeleer/oh-my-posh/code-changesnpx skills add JanDeDobbeleer/oh-my-posh --skill code-changesgit clone --depth 1 https://github.com/JanDeDobbeleer/oh-my-poshWhat 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 | $0.00088 | $0.01046 |
| Opus 5 | $0.00044 | $0.00523 |
| Sonnet 5 | $0.00018 | $0.00209 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
code-changes 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Changes
The workflow for going from an issue, pull request, idea, or feature request to shipped code. Follow the phases in order. Analysis always comes first; code comes last.
Each phase has a reference file with the full instructions. Read the reference file when you enter the phase — not before, and never skip it because the phase "looks obvious". Every phase boundary carries a named artifact — see references/artifacts.md — so a phase can be re-entered later (a Verify failure, an escalation answer) without re-deriving context from scratch.
Roles
Assign work based on model capability. The coordinator is not the strongest model — it's the one that stays resident, owns every phase by default, and knows when it's out of its depth.
-
Role: Coordinator
- Capability tier: Capable mid-tier, resident for the whole task
- Owns: Analysis, plan, delegation, supervision, verification, delivery — by default
-
Role: Escalation
- Capability tier: Strongest reasoning model available; invoked only on trigger
- Owns: The specific judgment call the coordinator flagged, then control returns
-
Role: Implementer
- Capability tier: Same tier as coordinator, or smaller for trivial edits
- Owns: Executing one pinned, self-contained task
-
Role: Trivial
- Capability tier: Small, fast model for mechanical, unambiguous edits
- Owns: Batched renames, config tweaks, typo fixes, doc touch-ups — never judgment calls
Concrete model names per vendor (Anthropic, OpenAI, Google) and how to run the split in Claude Code, GitHub Copilot, Codex, or IDE agents: references/model-tiers.md.
When the current agent already runs at implementer tier, there's no separate delegation step for standard work: plan and execute directly, still following every phase. Escalate to the strongest model only when a trigger fires — see references/escalate.md — never by default and never for a routine judgment call the coordinator is equipped to make itself.
What ships with it
11 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.
- references/analyze.md 3.1 KB
- references/artifacts.md 5.3 KB
- references/delegate.md 2.4 KB
- references/deliver.md 1.4 KB
- references/escalate.md 2.4 KB
- references/issue-triage.md 1.7 KB
- references/model-tiers.md 3.8 KB
- references/plan.md 3.2 KB
- references/pr-review-comments.md 2.8 KB
- references/supervise.md 3.6 KB
- references/verify.md 4.0 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.
- yesterday First seen · 81 lines · 88 tokens per session scan A 771a48bafca9
code-changes is a skill published in the GitHub repository JanDeDobbeleer/oh-my-posh (23,372 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,046 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
db
Database schema and query conventions for ThunderID. Use when changing schema scripts, defining SQL queries, updating store constants, or reviewing deployment-scoped persistence rules.
console
Navigate and interact with the ThunderID Console UI. Use when exploring the ThunderID admin console, testing UI changes, creating users/applications/roles, or debugging the frontend.
docs
Handles every ThunderID documentation task in one skill: scaffolding a new page, writing content into an existing page, checking structural standards, reviewing writing quality/tone/AI-vocabulary, verifying technical accuracy, reviewing API documentation (OpenAPI specs and SDK reference pages) for consistency and…
new-config
Interactively scaffold a new smug tmux session configuration (a YAML template). Use when the user wants to create, scaffold, or set up a new smug project/config file, or asks for "smug new config", "a smug template", or "/new-config". Walks the user through session name, root, windows, panes, commands, env, and hooks…
spec-init
面向新项目或现有项目的文档驱动开发 skill。Use when the user wants to create, 补齐, 更新, or refine project specs, run a Spec Kit-inspired workflow loop, maintain workflow/knowledge/change docs, analyze consistency, converge implementation back into docs, or update README/AGENTS for a real project.
release-sync
PromptHub release update skill. Use for /update-readme, version bumps, changelog updates, website sync, GUI screenshot/doc refresh, and multilingual release/documentation alignment.