undrift-check

undrift-check is a skill for Claude Code, Codex from larya-dot-eu/undrift. It costs 61 tokens per session (639 once invoked), scanned A, original, MIT.

A quick dashboard of Claude Code sessions across your projects, showing which projects are nearing the tool’s 50-session analysis window.

In plain words
What is it for?
Use it to count sessions, sort projects by activity, and spot projects that may need a deeper undrift check.
Why use it?
It gives you a fast overview before running a more detailed session review, without changing files or using extra agents.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Good fit Use it to count sessions, sort projects by activity, and spot projects that may need a deeper undrift check.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/larya-dot-eu/undrift/undrift-check
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 larya-dot-eu/undrift --skill undrift-check
Clone the repo
git clone --depth 1 https://github.com/larya-dot-eu/undrift

Made for: Claude Code, Codex.

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 undrift-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/larya-dot-eu/undrift/undrift-check/github.svg)](https://agentmods.dev/skills/larya-dot-eu/undrift/undrift-check)
Your own site
<a href="https://agentmods.dev/skills/larya-dot-eu/undrift/undrift-check"><img src="https://agentmods.dev/badge/skills/larya-dot-eu/undrift/undrift-check/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 undrift-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/larya-dot-eu/undrift/undrift-check"><img src="https://agentmods.dev/badge/skills/larya-dot-eu/undrift/undrift-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 639 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 $0.00061 $0.00639
Opus 5.5 $0.00024 $0.00256
Sonnet 5.5 $0.00012 $0.00128
Haiku 4.5 $0.00006 $0.00064

Measured 1mo ago against content hash 2c464cd53dd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

undrift-check 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 1mo 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/undrift-check/SKILL.md · 81 lines

What it actually says

Undrift Check — Session Count Dashboard

Run this for a quick overview of session counts across all your Claude Code projects.

Steps

1. Count sessions

Run:

home_slug=$(echo "$HOME" | tr '/' '-')
home_slug_escaped=$(echo "$home_slug" | sed 's/[.\\[*^$]/\\&/g')
for dir in ~/.claude/projects/*/; do
  [ -d "$dir" ] || continue
  count=$(find "$dir" -maxdepth 1 -name "*.jsonl" 2>/dev/null | wc -l | tr -d ' ')
  encoded=$(basename "$dir" | sed "s/^${home_slug_escaped}-//")
  base="$HOME" result="~" rest="$encoded"
  while [ -n "$rest" ]; do
    matched=0 i=${#rest}
    while [ $i -ge 1 ]; do
      seg="${rest:0:$i}"
      if [ -d "$base/$seg" ]; then
        result="$result/$seg" base="$base/$seg" rest="${rest:$i}"
        [ "${rest:0:1}" = "-" ] && rest="${rest:1}"
        matched=1; break
      fi
      i=$((i - 1))
    done
    [ $matched -eq 0 ] && { result="$result/${rest#-}"; break; }
  done
  echo "$count $result"
done | sort -rn

2. Format and display

Present the results as a table sorted by session count descending. Compute the status tier for each row:

  • ✓ fine — fewer than 40 sessions
  • ⚠ getting close — 40–44 sessions
  • 🔴 run now — 45 or more sessions (append remaining count)

Example:

Project                    Sessions   Status
─────────────────────────────────────────────
GitHubReps/pmcontext       47         🔴 run now  (3 remaining)
GitHubReps/seo-dash        44         ⚠ getting close
GitHubReps/linkedin        12         ✓ fine
GitHubReps/undrift          1         ✓ fine

3. Closing prompt

If any projects are 🔴, end with one line per flagged project:

→ Run /undrift-full on [project-name] to capture patterns.

If no projects exist yet, say: "No Claude Code project sessions found."

Hard Constraints

  • No file writes of any kind
  • No subagents
  • No CLAUDE.md modifications
  • Read-only operation
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. 1mo ago First seen · 81 lines · 61 tokens per session scan A 2c464cd53dd2

Subscribe to this mod's changes

undrift-check is a skill published in the GitHub repository larya-dot-eu/undrift (2 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 639 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

Cortex

LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…

danielmiessler/LifeOS · 184 tokens

rowboat-spaces

How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.

rowboatlabs/rowboat · 60 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens