vulyk: Skill for Claude Code

.claude/skills/_meta/insight-harvester/SKILL.md

insight-harvester is a skill for Claude Code from Black-coffe/vulyk. It costs 56 tokens per session (358 once invoked), scanned A, original, MIT.

A review tool that turns notes from coding sessions into evidence-backed patterns and proposed configuration changes. It groups repeated problems together instead of treating every observation as separate.

In plain words
What is it for?
Use it to analyze session learnings, find repeated causes of problems, and prepare small changes to project rules or agent instructions.
Why use it?
It helps distinguish recurring workflow friction from one-off incidents and ties proposed fixes to examples in the project. The result is a concrete configuration diff rather than general advice.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Black-coffe/vulyk's own configuration. It tells Claude Code how to work on vulyk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vulyk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Black-coffe/vulyk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Black-coffe/vulyk/main/.claude/skills/_meta/insight-harvester/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Black-coffe/vulyk

Made for: Claude Code.

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.

agentmods badge for insight-harvester

README.md
[![agentmods](https://agentmods.dev/badge/skills/black-coffe/vulyk/insight-harvester/github.svg)](https://agentmods.dev/skills/black-coffe/vulyk/insight-harvester)
Your own site
<a href="https://agentmods.dev/skills/black-coffe/vulyk/insight-harvester"><img src="https://agentmods.dev/badge/skills/black-coffe/vulyk/insight-harvester/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.

agentmods 80×15 button for insight-harvester

Your own site · 80×15
<a href="https://agentmods.dev/skills/black-coffe/vulyk/insight-harvester"><img src="https://agentmods.dev/badge/skills/black-coffe/vulyk/insight-harvester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 358 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.00358
Opus 5 $0.00028 $0.00179
Sonnet 5 $0.00011 $0.00072
Haiku 4.5 $0.00006 $0.00036

Measured 10d ago against content hash f1a757d1812e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

insight-harvester 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.

.claude/skills/_meta/insight-harvester/SKILL.md · 24 lines

What it actually says

Insight Harvester

Turn raw observations into configuration improvements with evidence.

Inputs

  • memory/learnings/*.md (raw, per-session) and memory/learnings/CONSOLIDATED.md
  • Pasted output of the built-in /insights command, when available
  • Recent docs/specs/*/ story files with ## Findings walls

Method

  1. Cluster, do not enumerate. Group observations by underlying cause, not surface symptom. "Worker touched out-of-scope file" three times across different specs is ONE pattern.
  2. Demand evidence. Every pattern cites at least 2 occurrences (file + date). Single events are noted, not acted on.
  3. Map pattern -> smallest fix. Prefer, in order: a path-scoped rule in .claude/rules/ > a line in an agent prompt > a CLAUDE.md constitution change (most expensive context-wise - last resort).
  4. Write fixes as diffs, not advice. "Add to .claude/rules/api.md: 'All new endpoints require an authz check; see wiki/auth-invariants'" - copy-pasteable.
  5. Specificity test: a rule that would equally apply to any random repo is too generic to add. Project-specific or nothing.

Output

A ranked table: pattern | evidence (n, links) | proposed diff | expected effect | rollback note.

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.

  1. 10d ago First seen · 24 lines · 56 tokens per session scan A f1a757d1812e

Subscribe to this mod's changes

insight-harvester is a skill published in the GitHub repository Black-coffe/vulyk (2 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 358 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 2026-08-31.