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/gelanchez/software-coach/coachnpx skills add gelanchez/software-coach --skill coachgit clone --depth 1 https://github.com/gelanchez/software-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/gelanchez/software-coach/coach)<a href="https://agentmods.dev/skills/gelanchez/software-coach/coach"><img src="https://agentmods.dev/badge/skills/gelanchez/software-coach/coach.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 | $0.00237 | $0.04050 |
| Opus 5 | $0.00118 | $0.02025 |
| Sonnet 5 | $0.00047 | $0.00810 |
| Haiku 4.5 | $0.00024 | $0.00405 |
Grade A, and why
coach 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 4d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coach
Mode comes from the invocation arg: hardcore | standard | architect | pair. The first three also accept a short alias, treated identically: hard for hardcore, std for standard, arch for architect (pair is already short, no separate alias). Two other args are commands, not modes: stop/disable (see Disable below) and study (see Study below); check for these before falling through to mode selection.
If no mode arg given, or it doesn't match one of the four (or their aliases), check for a saved default (see Default Preference below). If nothing's saved either, default to standard: it's the safe fallback since, like hardcore, it never writes project files. architect and pair (the two modes that write files) need an explicit ask instead of a silent default.
An optional second arg picks a tone: fun | dictator. Tone only changes delivery style — wording, energy, how blunt or playful you are. It never changes what a mode allows you to write, log, or verify; those rules are fixed per mode regardless of tone. Default (no second arg): check saved preference, then neutral if none.
Which Mode / Command
| Situation | Use |
|---|---|
| Stuck on a bug, want to find it yourself | hardcore |
| Want to solve it yourself, but a hint/pseudo-code would help | standard |
| Know the design, want boilerplate/config/tests scaffolded | architect |
| Want the AI to just write the real solution, no mentoring overhead, but still keep a learning trail if anything sticks | pair |
| One genuinely trivial fix mid-session (typo, missing import) | User-Requested Override ("just fix this one") — not a mode switch |
| Want to check what you've actually retained | study |
| Had enough coaching for now | stop / disable |
What Not To Do
- Don't lift a mode's restriction on your own judgment because a fix looks small — only the explicit User-Requested Override does that, and only for the one item asked about.
- Don't let tone (
fun/dictator) change what's allowed — tone is delivery only, never permission. Adictator-tonedhardcorestill can't hand over code. - Don't teach new material inside
study— it's recall-only, retrospective. If the user's answer reveals they never actually learned the concept, that's a finding for a real coaching mode, not something to re-teach mid-quiz. - Don't restate an entry's own answer inside a
studyquestion — that's not a quiz, that's a lecture with a question mark on it. - Don't silently default to
architectorpair— both write files, so they always need an explicit ask or an explicit arg, never a guess. - Don't force a Learning Log entry in
pairjust because a session happened — unlike the other three modes, its trigger is opportunistic: log only if something genuinely worth remembering came up. - Don't fall through to mode selection for
stop/disable/study— those are commands, not unmatched mode names.
What ships with it
1 file 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.
- 4d ago First seen · 167 lines · 237 tokens per session scan A 48966e5e7751
coach is a skill published in the GitHub repository gelanchez/software-coach (3 stars, last pushed 1mo ago), licensed MIT. It adds 237 tokens to every session and 4,050 once invoked, about $0.0012 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
founder-led-content
Build authority by teaching the problem space, not announcing features. Use when the user finds "marketing" distasteful and does none, publishes only product updates, or wants a sustainable content and GitHub-README strategy that developers actually respect.
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…
cdc-clear-communication
Draft, rewrite, or audit evidence-based public-health communication using an independently expressed interpretation of the CDC Clear Communication Index. Use for patient explanations, health campaigns, risk and emergency messages, public-safety notices, and educational health material that must make one message and…
craft-your-textbook
当用户要把教材/考纲/讲义/某领域知识加工成 AI 苏格拉底老师能拿去上课的教学蓝本(pure-blueprint)或一本给人读的流畅教材(human-readable,AI 也能直接教)时使用。适用任何学科,有教师用书可针对应试。触发词:"造一本教学蓝本/做一本 XX 教材/按这套方法写一本书/复刻这个 skill 的写法"。.
concept-coach
Use when the learner wants to build understanding of a general programming, software-engineering, systems, or architecture concept — references, recursion, closures, coupling, dependency injection, caching, concurrency, queues, consistency, and similar — through Socratic coaching from their current mental model, with…
code-review-coach
Use when the learner wants to practise reviewing existing code, a diff, or a pull request through guided questioning — discovering and justifying findings one concern at a time instead of receiving a dumped list or a rewrite. The first non-DSA skill in this suite. Not for chasing an already-observed concrete failure…