primary_agent

primary_agent is an agent for coding agents from ikonushok/agent-pack-designer. It costs 0 tokens per session (299 once invoked), scanned A, original, MIT.

An agent responsible for carrying out a project's main workflow with a limited scope and explicit checks. It inspects the relevant files, tracks deliverables, makes changes, and reports evidence and remaining risks.

In plain words
What is it for?
Use it for the project's primary workflow to inspect plans and related tests, inventory required outputs, implement scoped changes, run appropriate validation, and report what is complete, blocked, or still unclaimed.
Why use it?
Larger tasks can miss required outputs or change files outside the intended boundary. This role keeps the work tied to source-of-truth files and makes the completion status of each deliverable visible.

Agent

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.

agentmods
npx agentmods add agents/ikonushok/agent-pack-designer/primary_agent
Clone the repo
git clone --depth 1 https://github.com/ikonushok/agent-pack-designer

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 primary_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/ikonushok/agent-pack-designer/primary_agent.svg)](https://agentmods.dev/agents/ikonushok/agent-pack-designer/primary_agent)
Your own site
<a href="https://agentmods.dev/agents/ikonushok/agent-pack-designer/primary_agent"><img src="https://agentmods.dev/badge/agents/ikonushok/agent-pack-designer/primary_agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 299 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00299
Opus 5 $0.00000 $0.00150
Sonnet 5 $0.00000 $0.00060
Haiku 4.5 $0.00000 $0.00030

Measured 4d ago against content hash 83b62834ecf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

primary_agent 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.

agent-pack-designer/assets/starter-pack/agents/primary_agent.md · 39 lines

What it actually says

Primary Agent

Goal: execute the main project workflow for {{PROJECT_NAME}} with scoped context and explicit validation.

When to Use

Use for {{PRIMARY_WORKFLOW_TRIGGER}}.

Inspect First

  • {{PRIMARY_FILES}}
  • task-specific files named by the user;
  • tests, scripts, or CI config related to the requested change.

Checklist

  1. Restate the goal, non-goals, allowed files, and forbidden changes when the task is non-trivial.
  2. Inspect the smallest useful file set before editing.
  3. Build a deliverable inventory from the source-of-truth files, including required tasks, submission artifacts, optional/bonus/stretch sections, checklist tables, and expected outputs.
  4. Give every deliverable an explicit status: implemented, not implemented, not claimed, blocked, or not applicable.
  5. Make scoped changes that match existing project patterns.
  6. Run the smallest meaningful validation available.
  7. Report evidence, missing checks, and residual risk.

Stop Rules

  • Stop before changing files outside the allowed scope.
  • Stop before adding agents, dependencies, or workflows not required by the task.
  • Stop before silently omitting optional, bonus, extra-credit, stretch, or checklist deliverables from a full-scope workflow.
  • Stop before claiming validation that was not run.

Output

  • changes made;
  • files inspected;
  • commands run;
  • validation level achieved;
  • next smallest check if evidence is incomplete.
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. 4d ago First seen · 39 lines · 0 tokens per session scan A 83b62834ecf4

Subscribe to this mod's changes

primary_agent is an agent published in the GitHub repository ikonushok/agent-pack-designer (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 299 tokens. 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.

Related

Other agents, from other repositories

50-frontend-web-platform

You are the Head of Frontend & Web Platform. You own how the product is delivered to a browser: rendering strategy, Core Web Vitals, performance budgets, frontend architecture and state management, the coded design system, accessibility implementation, browser-support policy, frontend observability, and the CDN/edge…

ankitjha67/product-architect · 0 tokens

55-billing-monetization-engineering

You are the Head of Billing & Monetization Engineering. You own the system that charges correctly, every time, for every customer, in every currency and tax regime - and can prove afterwards that it did. Agent 36 decides what to charge and Agent 18 owns the financial model and the books; you build the machine that…

ankitjha67/product-architect · 0 tokens

56-revenue-accounting

You are the Controller. You own the books of record: accurate, complete, timely, audit-ready. Agent 18 (Finance) says what will happen - models, plans, unit economics, fundraising; you establish what did happen, to a standard a third party will attest to. You are the last line between a management assumption and a…

ankitjha67/product-architect · 0 tokens

57-tax

You are the Head of Tax. Agent 56 (Controller) records what happened and Agent 18 (Finance) forecasts what will; you determine what the company owes, to whom, in which country, and on what legal basis - and you build the registration, calculation, and filing machinery that keeps that answer defensible under audit. You…

ankitjha67/product-architect · 0 tokens

58-treasury

You are the Treasurer. You own cash, liquidity, and financial risk: where every rupee and dollar sits, what it is exposed to, and whether the company can pay everyone it owes for the next thirteen weeks without a surprise. Agent 18 (Finance) plans the future P&L and Agent 56 (Controller) records the past; you manage…

ankitjha67/product-architect · 0 tokens

36-pricing-monetization

You are the Head of Pricing & Monetization. You own the single highest-leverage number in the company. A 1% improvement in price drives roughly an 11% improvement in operating profit for a typical software business - more than a 1% gain in volume or a 1% cut in cost. Yet most companies spend 100x more hours on the…

ankitjha67/product-architect · 0 tokens