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-explain-backgit 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-explain-back)<a href="https://agentmods.dev/skills/hassaan146/forge-mentor/forge-explain-back"><img src="https://agentmods.dev/badge/skills/hassaan146/forge-mentor/forge-explain-back/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-explain-back"><img src="https://agentmods.dev/badge/skills/hassaan146/forge-mentor/forge-explain-back.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 | $0.00047 | $0.00522 |
| Opus 5 | $0.00023 | $0.00261 |
| Sonnet 5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
forge-explain-back 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.
What it actually says
Explaining it back
Decision 009: a step is finished when the tests pass, the review is clean, and the user can say what was built and why. This skill is the third one.
It is reflective, not graded. Nobody fails. The point is to surface the gap while it is still cheap to close, not to score anyone.
When it fires
After the tests pass and the review is clean — never before. Asking someone to explain code that is still broken teaches them the broken version.
Scale it to the step
A one-line change gets one question. A phase that introduced authentication gets three or four. A gate heavier than the work it guards trains the user to rush it.
Ask about the decision, not the syntax
Wrong: "what does this function return?" — that is reading, and they can see it.
Right, in roughly this order:
- What did we choose, and what did we turn down? ("We used a login service instead of building password handling ourselves.")
- Why, for this project? This is the one that matters. A right answer for the wrong reason is the gap.
- What would have to change for the other option to win? This is what separates a remembered answer from an understood one.
Reading the answer
- Solid — say so in one line and move on. Do not congratulate at length.
- Thin but right — fill the gap in two sentences, no quiz.
- Wrong or blank — re-teach the concept from a different angle, then ask once more. Never the same words again; if they did not land the first time they will not land the second.
Three attempts, then stop and escalate: record what did not land in the decision record and carry on. Decision 009's three-strike rule exists so a stuck user is not trapped by the gate meant to help them.
Never
- Never withhold working code as leverage. The code is already written and already theirs.
- Never make the user feel tested. "Say it back in your own words" beats "explain to me why".
- Never accept your own summary as their answer.
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 · 53 lines · 47 tokens per session scan A 2bae8cc14a36
forge-explain-back is a skill published in the GitHub repository Hassaan146/forge-mentor (22 stars, last pushed 24d ago), licensed MIT. It adds 47 tokens to every session and 522 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.