vulyk-evolve

vulyk-evolve is a command for Claude Code from Black-coffe/vulyk. It costs 23 tokens per session (392 once invoked), scanned A, original, MIT.

A weekly review command for finding repeated problems in an agent setup and proposing configuration, rule, prompt, or skill changes as a reviewable set of edits.

In plain words
What is it for?
Use it to identify friction, find unused skills to retire, suggest new reusable rules, and prepare a dated changeset with reasons and rollback notes.
Why use it?
It turns scattered learning notes and usage data into evidence-based maintenance suggestions, while leaving a person in control of what gets applied.

Command for Claude Code

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.

agentmods
npx agentmods add commands/black-coffe/vulyk/vulyk-evolve
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 vulyk-evolve

README.md
[![agentmods](https://agentmods.dev/badge/commands/black-coffe/vulyk/vulyk-evolve.svg)](https://agentmods.dev/commands/black-coffe/vulyk/vulyk-evolve)
Your own site
<a href="https://agentmods.dev/commands/black-coffe/vulyk/vulyk-evolve"><img src="https://agentmods.dev/badge/commands/black-coffe/vulyk/vulyk-evolve.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 392 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00023 $0.00392
Opus 5 $0.00012 $0.00196
Sonnet 5 $0.00005 $0.00078
Haiku 4.5 $0.00002 $0.00039

Measured 5d ago against content hash dbed3e71ca41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

vulyk-evolve 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 5d 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/commands/vulyk-evolve.md · 14 lines

What it actually says

Run the evolution cycle. Use the insight-harvester and skill-gardener skills - they define the method. "$ARGUMENTS"

  1. Harvest. Read memory/learnings/ (raw + CONSOLIDATED), memory/stats/skills.json, and - if the user can paste it - the output of the built-in /insights command (ask once; proceed without it if unavailable).
  2. Diagnose. Produce three lists with evidence: (a) top 3 friction patterns (repeated mistakes, expensive habits, recurring re-explanations); (b) skills/rules unused for 3+ weeks -> archive candidates; (c) patterns done manually 3+ times -> new skill/rule candidates.
  3. Propose. On a branch vulyk/evolve-<date>, write the actual diffs: edits to CLAUDE.md project profile, .claude/rules/, agent prompts, new skill scaffolds; move archived skills to .claude/skills/_graveyard/<name>/ adding RETIRED.md (date, reason, evidence). Append a CHANGELOG.md entry justifying EVERY change in one line each.
  4. Human gate. Present the changeset as a review: per-change rationale, expected effect, rollback note. Apply NOTHING to the main branch yourself. With --dry-run, stop after the diagnosis report.

Discipline notes: prefer deleting and tightening over adding - constitutions rot by accretion; a rule that fires rarely but prevents disasters stays (frequency is not the only signal - say when you keep something for severity reasons).

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. 5d ago First seen · 14 lines · 23 tokens per session scan A dbed3e71ca41

Subscribe to this mod's changes

vulyk-evolve is a command published in the GitHub repository Black-coffe/vulyk (2 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 392 once invoked, about $0.0001 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.