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 Hassaan146/forge-mentor --skill forge-teachinggit clone --depth 1 https://github.com/Hassaan146/forge-mentorWrote 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/hassaan146/forge-mentor/forge-teaching)<a href="https://agentmods.dev/skills/hassaan146/forge-mentor/forge-teaching"><img src="https://agentmods.dev/badge/skills/hassaan146/forge-mentor/forge-teaching/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/hassaan146/forge-mentor/forge-teaching"><img src="https://agentmods.dev/badge/skills/hassaan146/forge-mentor/forge-teaching.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 | $0.00040 | $0.01865 |
| Opus 5 | $0.00020 | $0.00932 |
| Sonnet 5 | $0.00008 | $0.00373 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
forge-teaching 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 10d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teaching a decision
The decision is the lesson. A user who cannot say why their app uses one approach over another does not own it, however well it runs.
Order, every time: teach → options → recommend → wait.
Teach first
Two or three sentences of plain language before the question. Assume no jargon (rule R1). Say what the thing is and what it decides for the rest of the project — not how it is spelled.
Logging in proves someone is who they say they are. Where that check happens decides how much of it you build and keep safe yourself.
Then the options
At least three, up to six, each with its real consequence. Never a category, name the actual thing (rule R2): "Postgres", not "a relational database". "Fable 5 teaches", not "the best-fit model".
Three is a floor, not a target, and the tools enforce it: render_decision refuses a block with
two options or with an option that has no consequence line. Two is a false binary, and a false
binary is a decision made by whoever picked the pair. This is not theoretical. A real run offered
"Docker, or run it locally" on a project that had already said it runs on one laptop: two options
where there were six, one of them ruled out three questions earlier.
Every option must be one a competent engineer might genuinely pick. A fake option to make the recommendation look obvious is a lie, and the user will feel it.
The menu belongs to this project, not to the topic. Pass project to render_decision and it
strikes out anything the recorded decisions have already excluded. Never put an excluded option
back. Never offer a container to a project that runs on one machine, accounts to a project with
one user, or hosted storage to a project with no server.
Say what is ruled out, and why. A struck-out option teaches more than a missing one: a user who reads "a container, ruled out because this runs only on your machine" has just learned what a container is for, and it cost no question.
A subject is not one question
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.
- 10d ago First seen · 166 lines · 40 tokens per session scan A 68c2d7aef817
forge-teaching is a skill published in the GitHub repository Hassaan146/forge-mentor (22 stars, last pushed 25d ago), licensed MIT. It adds 40 tokens to every session and 1,865 once invoked, about $0.0002 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
self-assessment
Interactive skill assessment with personalized learning path generation.
talk-stage5-script
Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.
talk-stage6-revision
Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.
talk-stage1-extract
Extracts and structures source material (articles, transcripts, notes) into a talk summary with narrative arc, themes, metrics, and gaps. Auto-detects REX vs Concept type. Use when starting a new talk from any source material or auditing existing material before committing to a talk.
talk-stage3-concepts
Builds a numbered, categorized concept catalogue from the talk summary and timeline, scoring each concept HIGH / MEDIUM / LOW for talk potential with optional repo enrichment. Use when you need a structured inventory of concepts before choosing a talk angle, or when assessing which ideas have the strongest…
explain
Explain code, concepts, or system behavior with adjustable depth levels.