A coaching workflow for improving how someone uses Claude Code. It reviews existing coaching rules, an AI fluency score, and behavioural insights.

Use it to review current coaching rules, check the fluency score, identify improvement areas, and receive personalised workflow guidance.

It turns usage patterns into specific areas for improvement instead of relying on general advice.

coaching — Skill for Claude Code by tombelieber

Install

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.

Any agent

npx skills add tombelieber/claude-view --skill coaching

Clone the repo

git clone --depth 1 https://github.com/tombelieber/claude-view

Made for: Claude Code.

Or install claude-view, the plugin that ships this one along with the rest of its 12 skills, 1 hook, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tombelieber/claude-view/coaching/github.svg)](https://agentmods.dev/skills/tombelieber/claude-view/coaching)

Your own site

<a href="https://agentmods.dev/skills/tombelieber/claude-view/coaching"><img src="https://agentmods.dev/badge/skills/tombelieber/claude-view/coaching/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tombelieber/claude-view/coaching"><img src="https://agentmods.dev/badge/skills/tombelieber/claude-view/coaching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,050 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium MCP Rug Pull · line 16
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.03050
Opus 5	$0.00023	$0.01525
Sonnet 5	$0.00009	$0.00610
Haiku 4.5	$0.00005	$0.00305

Measured 10d ago against content hash 8532aae01b6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

coaching 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.

Origin

Copies of this mod

8 near-identical copies found in the catalogue:

cv-usage — 88% identical, 57 lines differ
export-data — 88% identical, 53 lines differ
team-status — 86% identical, 55 lines differ
project-overview — 86% identical, 59 lines differ
daily-cost — 81% identical, 51 lines differ
live — 81% identical, 55 lines differ
search — 81% identical, 51 lines differ
session-recap — 80% identical, 50 lines differ

packages/plugin/skills/coaching/SKILL.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You have access to the claude-view MCP server which provides tools for monitoring, analyzing, and managing Claude Code sessions. The claude-view server must be running on localhost (it auto-starts via the plugin hook).

Important: All tool names are prefixed with mcp__claude-view__. When calling a tool, always use the full prefixed name.

Error handling: If a tool returns an error about the server not being detected, tell the user to start it with npx claude-view.

Coaching & Improvement

Help the user improve their Claude Code workflow through coaching rules and personalized recommendations.

Steps

Get current coaching rules. Call mcp__claude-view__coaching_list_rules to see what rules are already configured.
Get fluency score. Call mcp__claude-view__get_fluency_score to get the user's current AI Fluency Score.
Get behavioral insights. Call mcp__claude-view__insights_get_insights to identify areas for improvement.
Present coaching status:

## Coaching Dashboard

**AI Fluency Score:** [score]/100

### Active Coaching Rules
- [rule name]: [description]
(from coaching_list_rules)

### Improvement Areas
- [area]: [current behavior] -> [recommended behavior]
(derived from insights)

### Recommendations
- [specific, actionable tip based on score and insights]
- [specific, actionable tip]

If the user wants to add a rule, call mcp__claude-view__coaching_apply_rule with the rule content.
If the user wants to remove a rule, call mcp__claude-view__coaching_remove_rule with the rule identifier.
If no coaching rules exist, suggest starting with 1-2 rules based on the insights data — e.g. rules about commit frequency, session length, or prompt specificity.

Available Tools

Tool	Description
Session Tools
`list_sessions`	List sessions with filters
`get_session`	Get session details
`search_sessions`	Grep search across sessions
Stats Tools
`get_stats`	Dashboard statistics
`get_fluency_score`	AI Fluency Score (0-100)
`get_token_stats`	Token usage statistics
Live Tools
`list_live_sessions`	Currently running sessions
`get_live_summary`	Aggregate live session summary
Auth Tools
`auth_post_session`	auth session
`auth_delete_session`	auth session
`auth_get_status`	auth status
Classify Tools
`classify_start_classification`	Trigger a classification job.
`classify_cancel_classification`	Cancel a running classification job.
`classify_single_session`	Classify a single session synchronously.
`classify_get_classification_status`	Get classification status.
Claude Home Tools
`claude_home_list_claude_home`	home
Cli Tools
`cli_create_session`	- Create a new tmux-backed CLI session.
Coaching Tools
`coaching_list_rules`	- List all coaching rules from the rules directory.
`coaching_apply_rule`	- Create a new coaching rule file.
`coaching_remove_rule`	- Remove a coaching rule file.
Contributions Tools
`contributions_get_contributions`	Main contributions page data.
`contributions_get_branch_sessions`	Sessions for a branch.
`contributions_get_session_contribution`	Session contribution detail.
Devices Tools
`devices_list_devices_handler`	devices
`devices_terminate_others_handler`	others
`devices_delete_device_handler`	devices {device_id}
Export Tools
`export_sessions`	Export all sessions.
Facets Tools
`facets_facet_badges`	Quality badges (outcome + satisfaction) for the requested session IDs
`facets_trigger_facet_ingest`	Start facet ingest from the Claude Code insights cache
`facets_pattern_alert`	Check the most recent sessions for a negative satisfaction pattern
`facets_facet_stats`	Aggregate statistics across all session facets.
Health Tools
`health_config`	config
`health_check`	Health check endpoint.
`health_get_status`	Get index metadata and data freshness info.
Ide Tools
`ide_get_detect`	`GET /api/ide/detect` — return cached list of installed IDEs.
`ide_post_open`	`POST /api/ide/open` — open a file in the requested IDE.
Insights Tools
`insights_get_insights`	Compute and return behavioral insights.
`insights_get_benchmarks`	Compute personal progress benchmarks.
`insights_get_categories`	Returns hierarchical category data.
`insights_get_insights_models`	per-model usage aggregated from rollup tables.
`insights_get_insights_projects`	per-project usage aggregated from rollup tables.
`insights_get_insights_trends`	Get time-series trend data for charts.
`insights_list_invocables`	List all invocables with their usage counts.
Jobs Tools
`jobs_list_jobs`	List all active jobs.
Live Tools
`live_get_pricing`	- Return the model pricing table.
`live_dismiss_all_closed`	- Dismiss all recently closed (in-memory only).
`live_get_live_session`	- Get a single live session by ID.
`live_dismiss_session`	- Dismiss from recently closed (in-memory only).
`live_get_live_session_messages`	- Get the most recent messages for a live session.
Mcp Tools
`mcp_get_mcp_servers`	returns all deduplicated MCP server configurations.
Memory Tools
`memory_get_all_memories`	returns all memory entries grouped by scope.
`memory_get_memory_file`	read a single memory file.
`memory_get_project_memories`	returns memories for a specific project.
Monitor Tools
`monitor_snapshot`	- One-shot JSON snapshot of current resources.
Oauth Tools
`oauth_get_auth_identity`	`GET /api/oauth/identity`
`oauth_get_oauth_usage`	`GET /api/oauth/usage`
`oauth_post_oauth_usage_refresh`	`POST /api/oauth/usage/refresh`
Pairing Tools
`pairing_generate_qr`	Generate a QR payload via Supabase pair-offer.
Plans Tools
`plans_get_session_plans`	- returns plan documents for the session's slug.
Plugins Tools
`plugins_list_plugins`	- Unified view of installed + available plugins.
`plugins_list_marketplaces`	plugins marketplaces
`plugins_marketplace_action`	plugins marketplaces action
`plugins_refresh_all`	all
`plugins_refresh_status`	status
`plugins_list_ops_handler`	List all queued/running/completed ops.
`plugins_enqueue_op`	Enqueue a plugin mutation, return immediately.
Processes Tools
`processes_cleanup_processes`	processes cleanup
`processes_kill_process`	processes {pid} kill
Projects Tools
`projects_list_projects`	list all projects backed by the in-memory catalog.
`projects_list_project_branches`	List distinct branches with session counts.
`projects_list_project_sessions`	paginated sessions for one project.
Prompts Tools
`prompts_list_prompts`	List prompt history with optional search/filter.
`prompts_get_prompt_stats`	Aggregate prompt statistics.
`prompts_get_prompt_templates`	Detected prompt templates.
Providers Tools
`providers_list_providers`	providers with session counts (count > 0 only, Claude Code always first).
`providers_usage`	token/cost aggregates per foreign provider within a trailing window
Reports Tools
`reports_list_reports`	List all saved reports.
`reports_get_preview`	Aggregate preview stats for a date range.
`reports_get_report`	Get a single report.
`reports_delete_report`	Delete a report.
Sessions Tools
`sessions_get_active_sessions`	returns all active session files from ~/.claude/sessions/.
`sessions_list_branches`	Get distinct list of branch names across all sessions.
`sessions_estimate_cost`	cost estimation (Rust-only, no sidecar).
`sessions_session_activity`	Activity histogram for sparkline chart.
`sessions_session_activity_rich`	Full server-side activity aggregation.
`sessions_bulk_archive_handler`	sessions archive
`sessions_bulk_unarchive_handler`	sessions unarchive
`sessions_archive_session_handler`	sessions {id} archive
`sessions_get_file_history`	List all file changes for a session.
`sessions_get_file_diff`	history/:file_hash/diff?from=N&to=M
`sessions_get_session_hook_events`	Fetch hook events for a session.
`sessions_get_session_messages_by_id`	Get paginated messages by session ID.
`sessions_get_subagent_messages`	Paginated blocks for a sub-agent.
`sessions_unarchive_session_handler`	sessions {id} unarchive
`sessions_interact_handler`	Resolve a pending interaction (permission, question, plan, elicitation).
`sessions_get_interaction_handler`	Fetch the full interaction data for a session's pending interaction.
Settings Tools
`settings_get_claude_code_settings`	returns merged, redacted Claude Code settings.
`settings_get_settings`	Read current app settings.
`settings_update_settings`	Update app settings (partial).
`settings_update_git_sync_interval`	Update the git sync interval.
Share Tools
`share_create_share`	sessions {session_id} share
`share_revoke_share`	sessions {session_id} share
`share_list_shares`	shares
Stats Tools
`stats_ai_generation_stats`	AI generation statistics with time range filtering.
`stats_overview`	Aggregate usage statistics.
`stats_storage_stats`	Storage statistics for the settings page.
`stats_get_trends`	Get week-over-week trend metrics.
Sync Tools
`sync_indexing_status`	- lightweight JSON snapshot of indexing progress.
`sync_trigger_deep_index`	Trigger a full deep index rebuild.
`sync_trigger_git_sync`	Trigger git commit scanning (A8.5).
System Tools
`system_check_path`	Check whether a filesystem path still exists.
`system_get_system_status`	Get comprehensive system status.
`system_clear_cache`	Clear obsolete search cache.
`system_trigger_git_resync`	Trigger full git re-sync.
`system_trigger_reindex`	Trigger a full re-index.
`system_reset_all`	Factory reset all data.
Teams Tools
`teams_list_teams`	List all teams.
`teams_get_team`	Get team detail.
`teams_get_team_cost`	Get team cost breakdown.
`teams_get_team_inbox`	Get team inbox messages.
`teams_get_team_sidechains`	Get team member sidechains.
Telemetry Tools
`telemetry_set_consent`	Set telemetry consent preference.
`telemetry_ingest_event`	ingress for web journey events.
Turns Tools
`turns_get_session_turns`	- Per-turn breakdown for a historical session.
Webhooks Tools
`webhooks_list_webhooks`	list all webhooks (secrets excluded).
`webhooks_create_webhook`	create a new webhook (returns signing secret once).
`webhooks_get_webhook`	get a single webhook by ID.
`webhooks_update_webhook`	update an existing webhook (partial update).
`webhooks_delete_webhook`	remove a webhook from config and secrets.
`webhooks_test_send`	send a synthetic test payload.
Workflows Tools
`workflows_list_workflows`	workflows
`workflows_create_workflow`	workflows
`workflows_control_run`	workflows run {run_id} control
`workflows_list_workflow_runs`	workflows runs
`workflows_get_workflow_run_detail`	workflows runs {session_id} {run_id}
`workflows_get_workflow_agent_detail`	workflows runs {session_id} {run_id} agents {agent_id}
`workflows_get_workflow`	workflows {id}
`workflows_delete_workflow`	workflows {id}

Read the full file on GitHub · 238 lines

Files

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.

SKILL.md.tmpl 1.7 KB

Changes

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 · 238 lines · 47 tokens per session scan A 8532aae01b6e

Subscribe to this mod's changes

coaching is a skill published in the GitHub repository tombelieber/claude-view (105 stars, last pushed 8d ago), licensed MIT. It adds 47 tokens to every session and 3,050 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.

Building agents Claude Code ai-agents anthropic claude cli dashboard

rotator

Rotate to the next connected account with proven headroom when a usage limit hits. Triggers: /rotator, rotate the account, hit my session limit, hit the weekly limit, out of usage, switch account, no headroom left, which account has capacity. Uses the headroom CLI to pick the next eligible login in your configured…

domanski-ai/headroom · 84 tokens

caliber-testing

Writes Vitest tests following project patterns: tests/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment variable save/restore in beforeEach/afterEach, vi.clearAllMocks() lifecycle, and test file organization. Use when user says…

caliber-ai-org/ai-setup · 113 tokens

save-learning

Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…

caliber-ai-org/ai-setup · 71 tokens

coaching