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.
npx skills add alexgaoth/claude-tend --skill tendgit clone --depth 1 https://github.com/alexgaoth/claude-tendWrote 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.
[](https://agentmods.dev/skills/alexgaoth/claude-tend/tend)<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>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.
| Model | Per session | Once 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 |
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.
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: rootCLAUDE.md, nestedCLAUDE.mdfiles in directories you worked in, andAGENTS.md. - If the project keeps its agent docs in
AGENTS.md(noCLAUDE.md, orCLAUDE.mdis a symlink or one-line pointer to it), editAGENTS.mdinstead. CLAUDE.mdcan import other files via@pathlines. 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.mdor~/.claude/CLAUDE.mdhere — those are personal, not project docs. - No file at all? Create a root
CLAUDE.mdonly 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.
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.
- 8d ago First seen · 93 lines · 107 tokens per session scan A 66c39958c691
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.
Other skills, from other repositories
api-testing
HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.
bun-http-server
Use when building HTTP servers with Bun.serve, handling requests/responses, implementing routing, creating REST APIs, or configuring fetch handlers.
bun-jest-migration
Use when migrating from Jest to Bun's test runner, import compatibility, mocks, and config.
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.
cloudflare-workers-migration
Migrate to Cloudflare Workers from AWS Lambda, Vercel, Express, and Node.js. Use when porting existing applications to the edge, adapting serverless functions, or resolving Node.js API compatibility issues.
bun-test-coverage
Use for test coverage with Bun, --coverage flag, lcov reports, thresholds, and CI integration.