tsm: Instructions file for Codex

AGENTS.md

tsm AGENTS.md is an instructions file for Codex, OpenCode from tashian/tsm. It costs 2,122 tokens per session, scanned A, original, MIT.

Repository instructions for a macOS secrets manager split between a Go command-line program and a Swift background service. The service stores encrypted secrets and uses Touch ID, while the two parts communicate over a local socket.

In plain words
What is it for?
Use it when modifying, building, testing, or releasing the command-line client, encrypted vault service, local communication, or related tests.
Why use it?
The project has two languages, two executables, and a security-sensitive storage boundary. The instructions help an agent understand its layout and run the combined build and test commands correctly.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions .claude-plugin; positional $N argument; mentions Claude Code.

This is tashian/tsm's own configuration. It tells Codex and OpenCode how to work on tsm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tsm configures →

View source ↗ tashian/tsm
Reuse

Borrowing it

Nothing to install: this file belongs to tashian/tsm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tashian/tsm/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tashian/tsm

Made for: Codex, OpenCode.

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 tsm AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tashian/tsm/agents-md/github.svg)](https://agentmods.dev/instructions/tashian/tsm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tashian/tsm/agents-md"><img src="https://agentmods.dev/badge/instructions/tashian/tsm/agents-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.

agentmods 80×15 button for tsm AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tashian/tsm/agents-md"><img src="https://agentmods.dev/badge/instructions/tashian/tsm/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,122 This file is loaded in full into every session.
When invoked 2,122 The same file — it is already loaded in full.
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 $0.02122 $0.02122
Opus 5.5 $0.00849 $0.00849
Sonnet 5.5 $0.00424 $0.00424
Haiku 4.5 $0.00212 $0.00212

Measured 29d ago against content hash c2d8b5f7bab9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tsm AGENTS.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 29d 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.

AGENTS.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 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) in tsmd/ — 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

Build & test

just test                 # go test ./... + swift test (tsmd/)
just build                # both binaries → dist/bin/
cp dist/bin/tsm dist/bin/tsmd ~/.local/bin/
pgrep -fl "/.local/bin/tsmd" | awk '{print $1}' | xargs -r kill   # stop the old daemon before reinstalling

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

Tag-driven: git tag -a vX.Y.Z && git push origin vX.Y.Z triggers .github/workflows/release.yml. Full procedure and one-time setup are in RELEASING.md — read it before cutting a release. Rules that are easy to get wrong:

  • Tag the merge commit on main, never a feature branch. Expect one github-actions[bot] commit on main after every release (plugin version bump); pull before branching.
  • Don't hand-edit versions. npm/*/package.json stay 0.0.0 (workflow rewrites from the tag at publish time). plugin/.claude-plugin/plugin.json and .claude-plugin/marketplace.json are bumped and committed by the workflow — that one has to land in git because claude plugin update only refreshes when the manifest version changes.
  • Publish order is load-bearing. @tashian/tsm-darwin-arm64 publishes before the wrapper @tashian/tsm so optionalDependencies resolve. Don't reorder.
  • npm Trusted Publishing needs Node 24 / npm 11. Node 22's npm 10 silently publishes unauthenticated and 404s — don't downgrade setup-node.
  • Irreversible. A published npm version can't be re-published. Confirm the version before pushing the tag.

Read the full file on GitHub · 88 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. 29d ago Changed · +1 lines · +132 tokens per session c2d8b5f7bab9
  2. 1mo ago First seen · 87 lines · 1,990 tokens per session scan A f38326c9676a

Subscribe to this mod's changes

tsm AGENTS.md is an instructions file published in the GitHub repository tashian/tsm (10 stars, last pushed 10d ago), licensed MIT. It adds 2,122 tokens to every session, about $0.0085 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 2026-09-22.

Related

tsm AGENTS.md compared with instructions from other repositories

tsm AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tsm AGENTS.mdtashian/tsmInstructions file1010d agoMITA2,122Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode