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 Zproger/ConceptLoom --skill concept-coachgit clone --depth 1 https://github.com/Zproger/ConceptLoomWrote 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/zproger/conceptloom/concept-coach)<a href="https://agentmods.dev/skills/zproger/conceptloom/concept-coach"><img src="https://agentmods.dev/badge/skills/zproger/conceptloom/concept-coach/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/zproger/conceptloom/concept-coach"><img src="https://agentmods.dev/badge/skills/zproger/conceptloom/concept-coach.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 | $0.00048 | $0.00356 |
| Opus 5.5 | $0.00019 | $0.00142 |
| Sonnet 5.5 | $0.00010 | $0.00071 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
concept-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 today.
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
Concept Coach
Teach so the learner can recreate the conclusion from ideas they trust.
Read the coaching reference before beginning a learning session. Follow Locate, Weave, and Build without collapsing them into a generic explanation.
Learning sessions must survive restarts. Start a notebook and persist progress with loom_save_learning_state throughout the lesson. If the learner asks to continue or resume, call loom_load_learning_state before responding with lesson content.
After every learner response, persistence must be your next action. Save route approval as phase=build before asking the first teaching question. Assess checkpoints with sessionId and an exact nextStep; assessment saves progress in the same call. Never send the next lesson message first.
Use AskUserQuestion for preferences and for presenting checkpoint choices. Grade only knowledge questions, using loom_frame_checkpoint before asking and loom_assess_checkpoint after the learner selects keys.
Choose evidence-appropriate checkpoints: choice for recognition, free recall for reconstruction, prediction or debugging for application, and transfer for a new context. Record confidence when useful and pass a stable evidenceConcept. At resume, check loom_list_due_reviews before reteaching saved material.
Delegate source verification to the evidence-scout subagent when facts are uncertain or time-sensitive. Prefer a compact text diagram; use a Mermaid block only when it makes a larger relationship clearer. Wait for learner approval after proposing the dependency route.
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.
- today First seen · 21 lines · 48 tokens per session scan A de7097819b1c
concept-coach is a skill published in the GitHub repository Zproger/ConceptLoom (199 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 356 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.
concept-coach compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| concept-coachZproger/ConceptLoom | Skill | 199 | 1mo ago | MIT | A | 48 | Claude Code |
| hr-onboardingnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | today | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | today | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | yesterday | MIT | A | 81 | Claude Code |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | yesterday | Apache-2.0 | A | 25 | Claude Code, Codex |
| eli5companion-inc/feynman | Skill | 10k | 7d ago | MIT | A | 63 | Claude Code, Codex |