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/ultimaphoenix/dev-coach/assetsnpx skills add UltimaPhoenix/dev-coach --skill assetsgit clone --depth 1 https://github.com/UltimaPhoenix/dev-coachWrote 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/ultimaphoenix/dev-coach/assets)<a href="https://agentmods.dev/skills/ultimaphoenix/dev-coach/assets"><img src="https://agentmods.dev/badge/skills/ultimaphoenix/dev-coach/assets.svg" alt="Measured on agentmods" 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 | $0.00204 | $0.02543 |
| Opus 5 | $0.00102 | $0.01272 |
| Sonnet 5 | $0.00041 | $0.00509 |
| Haiku 4.5 | $0.00020 | $0.00254 |
Grade A, and why
devcoach 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 3d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
21 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/calibration.md 2.7 KB
- references/onboarding.md 12 KB
- references/review.md 3.5 KB
- static/favicon.svg 114 B
- static/relative-time.js 1.3 KB runs code
- static/style.css 4.7 KB
- static/vendor/alpinejs.min.js 44 KB runs code
- static/vendor/flatpickr-dark.min.css 19 KB
- static/vendor/flatpickr.min.css 16 KB
- static/vendor/flatpickr.min.js 49 KB runs code
- static/vendor/highlight.min.js 122 KB runs code
- static/vendor/hljs-dark.min.css 856 B
- static/vendor/hljs-light.min.css 856 B
- static/vendor/htmx.min.js 47 KB runs code
- static/vendor/icons/bitbucket.svg 285 B
- static/vendor/icons/github.svg 823 B
- static/vendor/icons/gitlab.svg 574 B
- static/vendor/icons/vscode.svg 4.3 KB
- static/vendor/marked.min.js 49 KB runs code
- static/vendor/tailwind.js 398 KB runs code
- static/vscode.svg 4.3 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.
- 3d ago First seen · 193 lines · 204 tokens per session scan A ccf19d9abe94
devcoach is a skill published in the GitHub repository UltimaPhoenix/dev-coach (4 stars, last pushed today), licensed AGPL-3.0. It adds 204 tokens to every session and 2,543 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
toolbelt
Toolbelt is a collaborative substrate over your data. Upload any document — entities and relationships extracted automatically, queryable immediately. Ask questions that span structured tables, documents, and relationships in a single call. No stitching databases together. Toolbelt orchestrates semantic, structured…
ml-pipeline
Use when building ML pipelines, orchestrating training workflows, automating model lifecycle, implementing feature stores, or managing experiment tracking systems.
spark-engineer
Use when building Apache Spark applications, distributed data processing pipelines, or optimizing big data workloads. Invoke for DataFrame API, Spark SQL, RDD operations, performance tuning, streaming analytics.
fine-tuning-expert
Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks. Invoke for parameter-efficient methods, dataset preparation, or model adaptation.
prompt-engineer
Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or structured outputs.
rag-architect
Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, or context augmentation.