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 grcengineering/companion --skill socratic-coachgit clone --depth 1 https://github.com/grcengineering/companionWrote 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/grcengineering/companion/socratic-coach)<a href="https://agentmods.dev/skills/grcengineering/companion/socratic-coach"><img src="https://agentmods.dev/badge/skills/grcengineering/companion/socratic-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 5.1 | $0.00056 | $0.00531 |
| Opus 5 | $0.00028 | $0.00266 |
| Sonnet 5 | $0.00011 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
socratic-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 7d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
socratic-coach
What
Guide the learner with short questions until they reveal the useful distinction, assumption, or next move themselves.
When
- The learner is stuck but not asking for a lecture.
- The learner is thinking aloud or has a vague intuition.
- The learner jumps to a conclusion without naming assumptions.
- The learner would benefit from generative struggle before explanation.
Not For
- A fully framed fictional scenario. Use
practice-scenario. - A direct concept explanation after the learner asks "what is X?" Use
concept-tutor. - A retrospective on completed work. Use
task-retrospective.
Inputs
- Learner's current claim, confusion, or draft thought.
- Optional profile signal about level and goals.
- Boundary risk from
brain/skill-router.md.
Steps
- Restate the learner's current question in learning-safe terms.
- Ask one sharp question about intent, signal, assumption, or tradeoff.
- Wait for the answer before adding information.
- Reflect the pattern you hear.
- Ask one transfer question.
- Summarize only after the learner has done the reasoning.
Validation
- The learner produces at least one insight before receiving the answer.
- Questions stay short and sequenced.
- The exchange does not become live operational advice.
Gotchas
- If the learner explicitly asks for a definition, do not withhold teaching; route to
concept-tutor. - If the learner is anxious or time-constrained, reduce the number of questions.
- If sensitive real details appear, ask for abstraction and keep coaching about reasoning.
Failure Modes
- Interrogation: ask one or two questions at a time.
- Vague coaching: every question should target a missing assumption or distinction.
- Advice drift: coach the thinking pattern, not the live decision.
Examples
- User says "I do not know how to think about this control" -> Ask what the control is supposed to change, then what evidence would prove that change.
- User says "This vendor feels risky" -> Ask what signal created that feeling, then abstract away from the real vendor.
- User says "Just tell me what risk means" -> Route to
concept-tutorbecause this is a concept request.
What ships with it
3 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.
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.
- 7d ago First seen · 63 lines · 56 tokens per session scan A 5f0e097cdb8f
socratic-coach is a skill published in the GitHub repository grcengineering/companion (33 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 531 once invoked, about $0.0003 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
control-mapping
Maps NIST controls to FedRAMP requirements and documents. Use when helping with control implementation, compliance mapping, security baseline alignment, or understanding control requirements.
frmr-analysis
Analyzes FedRAMP FRMR documents to extract control mappings, KSI entries, and version changes. Use when the user asks about FedRAMP requirements, control mappings, compliance data, or needs to understand FRMR document content.
GRC & Compliance
Governance, risk, and compliance — risk assessment and scoring, control mapping across NIST CSF 2.0 / ISO 27001:2022 / SOC 2 / CIS Controls v8, gap analysis, audit evidence preparation, and security policy generation.
performing-soc2-type2-audit-preparation
Automates SOC 2 Type II audit preparation including gap assessment against AICPA Trust Services Criteria (CC1-CC9), evidence collection from cloud providers and identity systems, control testing validation, remediation tracking, and continuous compliance monitoring. Covers all five TSC categories (Security…
hr-learning-development
Help HR business partners, L&D managers, and people development leaders understand, design, and run learning and development programs, skills gap analyses, career development frameworks, leadership development tracks, onboarding programs, and learning culture initiatives. Use when asked to design a learning program…
hr-mobile
Help HR managers, recruiters, and talent acquisition teams understand Mobile Development, iOS, Android, cross-platform engineering, mobile app architecture, and modern mobile ecosystems. Use when asked to explain mobile development, screen mobile developers, understand React Native or Flutter, compare native and…