tend

tend is a skill for Claude Code from alexgaoth/claude-tend. It costs 107 tokens per session (1,846 once invoked), scanned A, original, MIT.

A maintenance skill that updates a project's CLAUDE.md or AGENTS.md with useful facts learned during development and removes information that is no longer true. These files provide instructions to future coding-agent sessions.

In plain words
What is it for?
Use it after a significant change, debugging session, newly discovered repository rule, or correction to documented tooling.
Why use it?
It keeps shared project guidance short and accurate, so future agents are less likely to repeat discovered mistakes or follow outdated commands.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the tend plugin — 1 skill shipped together

Good fit Use it after a significant change, debugging session, newly discovered repository rule, or correction to documented tooling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexgaoth/claude-tend/tend
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 alexgaoth/claude-tend --skill tend
Clone the repo
git clone --depth 1 https://github.com/alexgaoth/claude-tend

Made for: Claude Code.

Or install tend, the plugin that ships this one along with the rest of its 1 skill.

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 tend

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexgaoth/claude-tend/tend.svg)](https://agentmods.dev/skills/alexgaoth/claude-tend/tend)
Your own site
<a href="https://agentmods.dev/skills/alexgaoth/claude-tend/tend"><img src="https://agentmods.dev/badge/skills/alexgaoth/claude-tend/tend.svg" alt="Measured on agentmods" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,846 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 $0.00107 $0.01846
Opus 5 $0.00053 $0.00923
Sonnet 5 $0.00021 $0.00369
Haiku 4.5 $0.00011 $0.00185

Measured 8d ago against content hash 66c39958c691, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tend 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 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.

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/tend/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tend — keep the project's CLAUDE.md true, short, and load-bearing

A project CLAUDE.md is read into every future session's context. Every line costs tokens in every session forever, so a line earns its place only by changing what an agent would do. You are as much a pruner as a writer: deleting a stale line is worth as much as adding a good one, and "nothing worth adding" is a valid outcome.

Run this in the session that did the work — the transcript is the input. A fresh subagent has nothing to harvest; never delegate this step.

If an argument was given, treat it as the focus area (e.g. /tend the build tooling), but still fix stale claims you notice elsewhere.

1. Find the files

  • Project root: git rev-parse --show-toplevel; outside a git repo, the directory the work happened in. In scope: root CLAUDE.md, nested CLAUDE.md files in directories you worked in, and AGENTS.md.
  • If the project keeps its agent docs in AGENTS.md (no CLAUDE.md, or CLAUDE.md is a symlink or one-line pointer to it), edit AGENTS.md instead.
  • CLAUDE.md can import other files via @path lines. Follow imports when reading, and when a fact's natural home is an imported file (e.g. @docs/testing.md), edit it there — never duplicate it in the importer.
  • Never edit CLAUDE.local.md or ~/.claude/CLAUDE.md here — those are personal, not project docs.
  • No file at all? Create a root CLAUDE.md only if step 2 produces real material. Never scaffold empty sections.

2. Harvest the session

Answer each question, collecting candidate facts:

  • What did I discover the hard way — by trial, error, or grep — that one line would have told me upfront?
  • Where was I wrong? A command that failed, a test I broke, a user correction, a review finding. What line would have prevented it?
  • What did the user state as a project rule ("always X", "never Y", "we use Z here")?
  • Which build / test / run / verify commands actually work, where the obvious guess fails?
  • What invariant does the code not announce? Generated files, pairs kept in sync by hand, ordering constraints, load-bearing hacks.
  • Which existing CLAUDE.md line did I misread, overlook, or find wrong? An instruction that failed to instruct is a bug — rewrite it so the next agent can't miss it.

Read the full file on GitHub · 93 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. 8d ago First seen · 93 lines · 107 tokens per session scan A 66c39958c691

Subscribe to this mod's changes

tend is a skill published in the GitHub repository alexgaoth/claude-tend (1 stars, last pushed 16d ago), licensed MIT. It adds 107 tokens to every session and 1,846 once invoked, about $0.0005 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.