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 agentmods add instructions/tashian/tsm/claude-mdgit clone --depth 1 https://github.com/tashian/tsmWrote 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/tashian/tsm/claude-md)<a href="https://agentmods.dev/instructions/tashian/tsm/claude-md"><img src="https://agentmods.dev/badge/instructions/tashian/tsm/claude-md.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 | $0.02333 | $0.02333 |
| Opus 5 | $0.01167 | $0.01167 |
| Sonnet 5 | $0.00467 | $0.00467 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
tsm 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 4d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tsm — Notes for Claude
tsm is a Touch-ID-gated secrets manager for macOS. Two halves in one repo:
- Go CLI (
tsm) at the repo root — user-facing commands and agent integration. - Swift daemon (
tsmd) intsmd/— owns the encrypted vault, Keychain, Touch ID, audit log.
They communicate via newline-delimited JSON-RPC 2.0 over a Unix socket. The CLI auto-spawns the daemon on first use.
Layout
go.mod, main.go # Go CLI entry
cmd/ # cobra subcommands (one file per command)
internal/
client/ # JSON-RPC Unix socket client + Caller interface
daemon/ # tsmd lifecycle (spawn, wait-for-socket)
jsonrpc/ # JSON-RPC 2.0 types
normalize/ # Kebab() — derives ids from display names
paths/ # XDG path resolution
tsmd/ # SwiftPM package (the daemon)
Sources/tsmd/ # one .swift file per concern
Tests/tsmdTests/ # XCTest, ~83 tests
docs/plans/ # design + implementation plans (read these first)
Build & test
# Daemon (Swift, run from tsmd/)
cd tsmd && swift test
cd tsmd && swift build -c release
cp tsmd/.build/release/tsmd ~/.local/bin/tsmd
# CLI (Go, run from repo root)
go test ./...
go build -o ~/.local/bin/tsm .
# Stop a running daemon before reinstalling so pgrep + kill, e.g.:
pgrep -fl "/.local/bin/tsmd" | awk '{print $1}' | xargs -r kill
The daemon must be ad-hoc signed (Apple Silicon requirement). swift build does this automatically. Do not run codesign --remove-signature on the binary.
Releasing
Releases are tag-driven. Pushing a vX.Y.Z tag triggers .github/workflows/release.yml (on a macos-15 runner), which builds the binaries, creates the GitHub release (tarball + checksums.txt, auto-generated notes), and publishes both npm packages.
To cut a release: make sure main is green and synced, then
git tag -a v0.1.11 -m "v0.1.11 ..." && git push origin v0.1.11
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.
- 4d ago First seen · 113 lines · 2,333 tokens per session scan A 9995488e1b58
tsm CLAUDE.md is an instructions file published in the GitHub repository tashian/tsm (9 stars, last pushed 3mo ago), licensed MIT. It adds 2,333 tokens to every session, about $0.0117 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 instructions, from other repositories
claude-cybersecurity-skill CLAUDE.md
Claude Code instructions for pitimon/claude-cybersecurity-skill, covering claude.md, what this is, architecture, how it works at runtime and key files.
cyber-nexus CLAUDE.md
Claude Code instructions for cyberstrat-forge/cyber-nexus, covering claude.md - ai 助手工作指南, 项目概述, 技术栈, 项目结构 and 插件脚本.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.