Borrowing it
Nothing to install: this file belongs to alexgaoth/claude-tend. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alexgaoth/claude-tend/main/CLAUDE.mdgit 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/instructions/alexgaoth/claude-tend/claude-md)<a href="https://agentmods.dev/instructions/alexgaoth/claude-tend/claude-md"><img src="https://agentmods.dev/badge/instructions/alexgaoth/claude-tend/claude-md/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.
<a href="https://agentmods.dev/instructions/alexgaoth/claude-tend/claude-md"><img src="https://agentmods.dev/badge/instructions/alexgaoth/claude-tend/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00618 | $0.00618 |
| Opus 5.5 | $0.00247 | $0.00247 |
| Sonnet 5.5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
claude-tend CLAUDE.md 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 2mo 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Gotchas
- Every failure path in
hooks/stop-nudge.pymust print nothing and exit 0 — output or a traceback there surfaces as an error on the user's Stop event. New code goes inside the existing guards; a new failure mode gets its own silent return. - The hook dedupes via
${TMPDIR:-/tmp}/claude-tend-nudge-<session_id>. Re-running with the same session_id is silently a no-op — delete the marker between manual tests, or the nudge "mysteriously" won't fire. - The skill name
tendis kept in sync by hand across four places: theskills/tend/directory name, the SKILL.md frontmattername:,.claude-plugin/plugin.json, and thepluginsentry in.claude-plugin/marketplace.json. A rename or a new skill must touch all of them. skills/tend/SKILL.mdstays under ~120 lines and its frontmatter description under 1024 chars — the description is what drives model auto-invocation, and the skill must practice the budget it preaches.- Shell commands printed inside
skills/tend/SKILL.mdare contract, not illustration — run each one, from a subdirectory, before committing a change to it.git ls-files <path>returns 0 rather than an error from the wrong cwd, so a plausible-looking pathspec silently floors the computed budget to its smallest band. - The nudge
reasonmust cap the model's reply length and forbid repeating the previous answer — wording that asks it to "restate the summary" makes it paste the entire answer twice. - README behavior claims are testable guarantees (fail-silent, once-per-session, git-repos-only), not prose: any change to hook or skill behavior must update the matching README sentence.
- The budget bands (40/60/80/100 lines, by governed file count) are stated in full in both
skills/tend/SKILL.mdand README's philosophy section. Retune one and the other drifts silently — there is no test to catch it.
Testing the hook
No test framework — verify by piping payloads from the repo root:
echo '{"session_id":"t1","cwd":"'$PWD'"}' | python3 hooks/stop-nudge.py # block JSON, exit 0
# same session_id again → silence; "stop_hook_active": true → silence; non-git cwd → silence
echo not-json | python3 hooks/stop-nudge.py # silence, exit 0
rm -f "${TMPDIR:-/tmp}/claude-tend-nudge-t1"
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.
- 2mo ago First seen · 24 lines · 618 tokens per session scan A 8cf9b2044a93
claude-tend CLAUDE.md is an instructions file published in the GitHub repository alexgaoth/claude-tend (1 stars, last pushed 2mo ago), licensed MIT. It adds 618 tokens to every session, about $0.0025 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.