achievements

achievements is a skill for Claude Code from vibeeval/vibecosystem. It costs 33 tokens per session (1,933 once invoked), scanned A, original, MIT.

A game-like progress system for software development, with experience points, levels, streaks, and achievements grouped into skill trees.

In plain words
What is it for?
Recording milestones such as writing code, fixing bugs, completing reviews, shipping features, and collaborating with agents.
Why use it?
It gives developers a way to track progress and keep regular coding habits visible.

Skill for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths.

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 skills/vibeeval/vibecosystem/achievements
Any agent
npx skills add vibeeval/vibecosystem --skill achievements
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

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 achievements

README.md
[![agentmods](https://agentmods.dev/badge/skills/vibeeval/vibecosystem/achievements.svg)](https://agentmods.dev/skills/vibeeval/vibecosystem/achievements)
Your own site
<a href="https://agentmods.dev/skills/vibeeval/vibecosystem/achievements"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/achievements.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,933 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 $0.00033 $0.01933
Opus 5 $0.00016 $0.00966
Sonnet 5 $0.00007 $0.00387
Haiku 4.5 $0.00003 $0.00193

Measured 2d ago against content hash 98996787adb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

achievements 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 2d 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.

skills/achievements/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.

Achievement System

Steam-style gamification for the development workflow. Earn XP by coding, fixing bugs, shipping features, and collaborating with agents. Level up, maintain streaks, and unlock achievements across 5 skill trees.

XP Level Thresholds

Level XP Required Title
1 0 Apprentice
2 100 Developer
3 300 Engineer
5 500 Senior Engineer
10 1000 Staff Engineer
20 3000 Principal Engineer
50 10000 Legendary

Streak System

Consecutive days of coding activity multiply XP earned:

Streak Multiplier
1-2 days 1.0x
3-6 days 1.25x
7-13 days 1.5x
14-29 days 2.0x
30+ days 3.0x

Missing a day resets the streak to 0.

Skill Trees

Tree 1: Code Warrior

Achievements for writing and shipping code.

First Blood (10 XP)

  • Description: Complete your first code review
  • Unlock: First time a commit or diff is reviewed in a session
  • Badge: Sword icon

Speed Demon (25 XP)

  • Description: Fix a bug in under 2 minutes from identification to resolution
  • Unlock: Bug-fix tool sequence completes in < 120 seconds
  • Badge: Lightning bolt

Polyglot (50 XP)

  • Description: Work in 3 or more programming languages in a single session
  • Unlock: Edit files with 3+ distinct language extensions in one session
  • Badge: Globe

Marathon Runner (100 XP)

  • Description: Sustain an 8-hour coding session without stopping
  • Unlock: Session active for 8+ hours (tracked via tool call timestamps)
  • Badge: Running figure

Perfectionist (50 XP)

  • Description: All tests pass on the very first run after a feature implementation
  • Unlock: Test suite passes immediately after the first Write/Edit sequence with no retries
  • Badge: Gold star

Tree 2: Bug Slayer

Achievements for hunting and eliminating bugs.

Bug Whisperer (25 XP)

  • Description: Fix 5 bugs in a single session
  • Unlock: 5 bug-fix tool sequences detected in one session
  • Badge: Magnifying glass

Read the full file on GitHub · 238 lines

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. 2d ago First seen · 238 lines · 33 tokens per session scan A 98996787adb4

Subscribe to this mod's changes

achievements is a skill published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 33 tokens to every session and 1,933 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 2026-09-03.