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 JotJunior/cstk --skill apply-insightsgit clone --depth 1 https://github.com/JotJunior/cstkWrote 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/jotjunior/cstk/apply-insights)<a href="https://agentmods.dev/skills/jotjunior/cstk/apply-insights"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/apply-insights.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 | $0.00066 | $0.02289 |
| Opus 5 | $0.00033 | $0.01144 |
| Sonnet 5 | $0.00013 | $0.00458 |
| Haiku 4.5 | $0.00007 | $0.00229 |
Grade C, and why
apply-insights scanned grade C with 1 finding 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- [ ] PreToolUse: guards against destructive operations (rm -rf, DROP TABLE, force-push) How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Apply Usage Insights
Analyze the current project and apply relevant insights from usage patterns to improve Claude Code effectiveness.
Arguments
$ARGUMENTS should optionally specify a focus area:
- bugfix — Apply bug fix protocol and debugging improvements
- migrations — Apply database migration safety guidelines
- conventions — Apply code convention checks (enum/DTO matching)
- hooks — Suggest hooks for automated quality gates
- all — Full analysis and recommendations (default)
Step 1: Load Insights (data-driven first)
There are TWO possible sources. Prefer the facets digest — it reflects the
user's ACTUAL recent sessions (current, structured, project-specific), whereas
the curated .md is hand-written and often stale / from a different project.
Primary: facets digest (native /insights output)
The native /insights command writes per-session analyses to
~/.claude/usage-data/facets/*.json (fields: goal_categories, outcome,
friction_counts, friction_detail, claude_helpfulness,
user_satisfaction_counts, …). Aggregate them into a digest:
# Resolve the skill dir: installed copy first, repo source when developing.
DIGEST="$HOME/.claude/skills/apply-insights/scripts/digest-facets.sh"
[ -x "$DIGEST" ] || DIGEST="$(git rev-parse --show-toplevel 2>/dev/null)/plugins/cstk/skills/apply-insights/scripts/digest-facets.sh"
"$DIGEST" # markdown digest on stdout; optional: --top N --samples N
If it prints a digest (non-empty stdout), use it as the primary, data-driven
input. The ranked friction_counts + concrete friction_detail samples are
the key signal for recommendations (which friction recurs, with examples).
Fallback chain (graceful)
digest-facets.sh exits 0 with empty stdout when jq or the facets dir are
absent — so branch on emptiness:
- Facets digest non-empty → use it (preferred).
- Else read
~/.claude/insights/usage-insights.md(curated; may be stale) — and say so to the user. - Else neither exists → general best practices, explicitly labeled as generic / not data-driven.
What ships with it
2 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.
- 8d ago First seen · 220 lines · 66 tokens per session scan C 64775884b4ce
apply-insights is a skill published in the GitHub repository JotJunior/cstk (23 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 2,289 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…