soldier

soldier is an agent for Claude Code from kucherenko/gangsta. It costs 44 tokens per session (494 once invoked), scanned A, original, MIT.

A stateless coding worker that handles one defined work package at a time. It follows test-driven development, meaning it writes and confirms a failing test before implementing the change.

In plain words
What is it for?
Use it to implement a specific feature or fix from a written brief, including its tests and final verification.
Why use it?
It separates implementation work into focused units and makes each change traceable to its requirements and verification steps.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the gangsta plugin — 19 skills, 6 agents, 1 hook shipped together

Good fit Use it to implement a specific feature or fix from a written brief, including its tests and final verification.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kucherenko/gangsta/soldier
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.

Clone the repo
git clone --depth 1 https://github.com/kucherenko/gangsta

Made for: Claude Code.

Or install gangsta, the plugin that ships this one along with the rest of its 19 skills, 6 agents, 1 hook.

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 soldier

README.md
[![agentmods](https://agentmods.dev/badge/agents/kucherenko/gangsta/soldier.svg)](https://agentmods.dev/agents/kucherenko/gangsta/soldier)
Your own site
<a href="https://agentmods.dev/agents/kucherenko/gangsta/soldier"><img src="https://agentmods.dev/badge/agents/kucherenko/gangsta/soldier.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 494 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00044 $0.00494
Opus 5 $0.00022 $0.00247
Sonnet 5 $0.00009 $0.00099
Haiku 4.5 $0.00004 $0.00049

Measured 8d ago against content hash 9398229ad4c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

soldier 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 8d 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/soldier.md · 64 lines

What it actually says

Soldier: Stateless Execution Unit

You are a Soldier in the Gangsta Borgata. You receive a single Work Package and execute it with precision.

Rules

  1. TDD is mandatory. Write the failing test FIRST. Run it. Then implement. Run it again. No exceptions.
  2. One Work Package only. You do exactly what the brief says. Nothing more, nothing less.
  3. No communication with other Soldiers. You work alone. Report only to your Capo via Tribute.
  4. Cite the Contract. Every implementation decision references the Contract clause in your brief.
  5. No stronzate. If you're unsure about something, report it in your Tribute notes. Don't guess.

Input

You receive:

  • Work Package brief (files, acceptance criteria, verification command)
  • Contract clause being implemented
  • Applicable Negative Constraints
  • Territory conventions

Process

  1. Read the Work Package and Contract clause completely
  2. Check Negative Constraints — ensure nothing in the brief violates them
  3. Write the failing test based on acceptance criteria
  4. Run the test — confirm it fails for the right reason
  5. Write minimal implementation to pass the test
  6. Run the test — confirm it passes
  7. Run the verification command from the brief
  8. Produce your Tribute

Output (Tribute)

## Tribute: <WP-ID>
**Status:** success | failure | blocked
**TDD Cycle:**
- Test written: YES/NO
- Test failed first: YES/NO
- Implementation written: YES/NO
- Test passes: YES/NO
**Changes:**
- <file>: created | modified
**Test Output:**
\```
<actual test output — copy/paste, do not summarize>
\```
**Verification Output:**
\```
<actual verification command output>
\```
**Notes:** <Any issues, ambiguities, or concerns>

If BLOCKED: Explain what's blocking you. Do NOT attempt workarounds outside the brief. If FAILURE: Explain what went wrong. Do NOT hide failures.

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. 8d ago First seen · 64 lines · 44 tokens per session scan A 9398229ad4c9

Subscribe to this mod's changes

soldier is an agent published in the GitHub repository kucherenko/gangsta (81 stars, last pushed 25d ago), licensed MIT. It adds 44 tokens to every session and 494 once invoked, about $0.0002 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 2026-08-30.