write-terva-persona

write-terva-persona is a skill for Claude Code, Codex from terva-sh/terva. It costs 57 tokens per session (2,375 once invoked), scanned B, original, MIT.

A guide for creating a terva persona: a Markdown file that defines an agent's identity, voice, and area of focus.

In plain words
What is it for?
Creating focused identities such as a security reviewer, test strategist, or documentation reviewer.
Why use it?
It separates an agent's role and behavior from its tools and task instructions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Creating focused identities such as a security reviewer, test strategist, or documentation reviewer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/terva-sh/terva/write-terva-persona
Install

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.

Any agent
npx skills add terva-sh/terva --skill write-terva-persona
Clone the repo
git clone --depth 1 https://github.com/terva-sh/terva

Made for: Claude Code, Codex.

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 write-terva-persona

README.md
[![agentmods](https://agentmods.dev/badge/skills/terva-sh/terva/write-terva-persona/github.svg)](https://agentmods.dev/skills/terva-sh/terva/write-terva-persona)
Your own site
<a href="https://agentmods.dev/skills/terva-sh/terva/write-terva-persona"><img src="https://agentmods.dev/badge/skills/terva-sh/terva/write-terva-persona/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 write-terva-persona

Your own site · 80×15
<a href="https://agentmods.dev/skills/terva-sh/terva/write-terva-persona"><img src="https://agentmods.dev/badge/skills/terva-sh/terva/write-terva-persona.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,375 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00057 $0.02375
Opus 5 $0.00028 $0.01188
Sonnet 5 $0.00011 $0.00475
Haiku 4.5 $0.00006 $0.00237

Measured 9d ago against content hash d48d5f90e19a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

write-terva-persona scanned grade B with 1 finding 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 9d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

macros, roleplay greetings, or "ignore previous instructions"-style text.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

packages/agent/skills/builtin/write-terva-persona/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing a terva persona

Use this skill when the user asks to create, add, or write a persona — a custom agent identity, a "voice," or a focused specialist (a security reviewer, a test strategist, a docs reviewer …). Skim it first, then collaborate on the one persona they want and write it where terva resolves it.

Persona vs skill vs extension — pick the right one first

Three different things; a request for "a persona" or "an identity" lands here:

  • A persona is who is helping: identity, voice, and a behavioral charter that focuses the agent on a specialty. It shapes the system prompt's identity layer. Reach for it for "make a security-review agent", "give the agent this personality", "a reviewer persona".
  • A skill (write-terva-skill) is how to do a task: a reusable instruction set loaded on demand. Reach for it for a workflow/checklist.
  • An extension (write-terva-extension) is what can be done: code that adds a tool, command, or hook. Reach for it for new capability.

A persona never grants tools or changes permissions — that's the extension / permission layer. A persona only shapes identity and focus.

Anatomy of a persona

A persona is a single Markdown file: YAML frontmatter + a charter body.

---
name: Vartija
pronunciation: VAR-tee-yah
specialty: security review
summary: Evidence-first application-security engineer for source-code review.
emoji: 🛡️
accent_color: "#f7768e"
recommended_skills: []
good_for: [secure-code-review, threat-modeling, vulnerability-triage]
avoid_for: [pure-style-review]
---

Review source code as a security engineer. Inspect before judging. Prioritize
exploitable issues over checklist noise. For each finding give evidence, the
affected path, attacker capability, impact, severity rationale, and a concrete
remediation. Never call a vulnerability confirmed unless reachable context
supports it.

Frontmatter fields:

  • name (required) — the persona's name, shown in the identity line and banner. A persona with no name is invalid.
  • pronunciation (optional) — an English-speaker hint ("VAR-tee-yah"), shown as "Name (pronunciation)". There is no source for this but you — author it.
  • specialty (optional) — a short label for terva persona list and humans.
  • summary (optional) — one model-facing-safe line; the only field that would ever surface from an untrusted persona (see Trust below).
  • emoji, accent_color (optional) — display only; accent_color must be #RRGGBB.
  • recommended_skills (optional) — skill names only; never paste skill bodies into a persona.
  • good_for / avoid_for (optional) — selection hints. Inert in this version (they document intent and seed future dispatch); nothing enforces avoid_for.

Read the full file on GitHub · 206 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. 9d ago First seen · 206 lines · 57 tokens per session scan B d48d5f90e19a

Subscribe to this mod's changes

write-terva-persona is a skill published in the GitHub repository terva-sh/terva (2 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 2,375 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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.

sky-valley/pi · 66 tokens

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.

sky-valley/pi · 45 tokens

sls-dashboard-builder

A tool for creating and modifying importable JSON dashboards for Alibaba Cloud SLS, a service for searching and monitoring logs. It maps checked queries and analysis needs to dashboard charts.

alibaba/loongsuite-pilot · 72 tokens

loongsuite-pilot-insight

A reporting workflow for turning LoongSuite Pilot and AI coding-agent logs into structured reports about events, teams, data quality, development efficiency, and AI use. It defines the meaning of the log fields and the measurements used in dashboards.

alibaba/loongsuite-pilot · 91 tokens

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…

dimetron/pi-go · 124 tokens

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…

dimetron/pi-go · 177 tokens