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 skills/terva-sh/terva/init-workspacenpx skills add terva-sh/terva --skill init-workspacegit clone --depth 1 https://github.com/terva-sh/tervaWrote 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/terva-sh/terva/init-workspace)<a href="https://agentmods.dev/skills/terva-sh/terva/init-workspace"><img src="https://agentmods.dev/badge/skills/terva-sh/terva/init-workspace.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 | $0.00058 | $0.00941 |
| Opus 5 | $0.00029 | $0.00470 |
| Sonnet 5 | $0.00012 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
init-workspace 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 5d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize a workspace
Write the repository AGENTS.md: the standing instructions that terva loads
into every session that works here. The file rides every prompt, so every
line must earn its place. This skill is as much about what to leave out as
what to put in.
How terva loads it: $TERVA_HOME/AGENTS.md (the user's own cross-repo
preferences) first, then AGENTS.md files from the top-most parent directory
down to the working directory. A later file overrides an earlier one. So:
repository facts go in the repository AGENTS.md. Personal preferences go in
the global one. A subdirectory of a monorepo can layer its own on top. Do not
mix these scopes.
Survey before you write
Read, do not guess. In order:
- Existing instructions:
AGENTS.mdfirst, then any sibling instruction files other tools left behind (CLAUDE.md,.cursorrules,CONTRIBUTING). Mine them. If aCLAUDE.mdduplicates what you will write, say so to the user. Do not silently fork the two. - The build system: justfile or Makefile,
package.jsonscripts, CI workflow files. These are the source of truth for commands. - The layout: top-level directories, and where the code, the tests, and the documentation live.
- Convention signals: linter and formatter configuration, and a few representative source files for naming and comment style.
Verify every command you intend to record: run it. When a run is too
heavy (a full test suite), confirm the command exists in the build file and
say which. A stale command in AGENTS.md is worse than none: it fails in
every future session.
What belongs (and what does not)
In, roughly in this order:
- Commands: build, test (and how to run one test), lint, format, run. One line each.
- Architecture in five lines: the map a newcomer needs before their first edit. Major components and where they live. Not a tour.
- Conventions that differ from defaults: what a competent agent would otherwise get wrong. House style the linter already enforces needs no restatement.
- Policy: what must not change or go into a commit (generated files, vendored trees, secrets), and the required workflow (branch rules, how a PR opens).
- Gotchas: the traps that cost someone an hour. One line each, with the tell that identifies the trap.
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.
- 5d ago First seen · 84 lines · 58 tokens per session scan A a47874f6d577
init-workspace is a skill published in the GitHub repository terva-sh/terva (2 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 941 once invoked, about $0.0003 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
pi-sync
Daily upstream-sync job for the pi Go port — fetch upstream pi, triage every change since the recorded pin, port what's in scope, verify idiomatic + parity via independent reviews, update the ledger, and push. Use for "sync with upstream", "porting job", or as the scheduled daily run.
pi-go-review
Review ported Go code for idiomatic quality — that the port maximizes Go rather than transliterating TypeScript. Use after porting upstream pi changes, or standalone on any diff in this repo.
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
modern-go
Modernize Go code by applying version-appropriate idioms and APIs (gofix-style transformations). Scans go.mod for the Go version, then transforms Go source files to use modern patterns—from Go 1.0 through 1.26+. Use when the user says "现代化","现代Go语言", "地道的", "idiomatic", "modernize", "modern-go", "update Go code"…
code-guidelines-go
Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…
go-127
What changed in Go 1.27 (released August 2026) and how it changes the way Go is written in pi-go. Use this skill when writing or reviewing Go that could use a 1.27 feature, when bumping the go directive in go.mod, when a build or test behaves differently after a toolchain upgrade, or when code-guidelines-go points…