engineer

An implementation role that makes and verifies code, test, documentation, and infrastructure changes.

In plain words
What is it for?
Use it for coding, bug fixes, refactoring, test writing, documentation, shell scripts, and infrastructure work, with the appropriate language-specific guidance.
Why use it?
It gives the agent responsibility for applying changes and requires it to run the relevant build, tests, and checks before reporting completion.

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/alexei-led/cc-thingz/engineer
Clone the repo
git clone --depth 1 https://github.com/alexei-led/cc-thingz
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 425 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 $0.00070 $0.00425
Opus 5 $0.00035 $0.00212
Sonnet 5 $0.00014 $0.00085
Haiku 4.5 $0.00007 $0.00042

Measured 2d ago against content hash 7b44068ebc69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineer 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 2d 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.

src/agents/engineer.md · 37 lines

What it actually says

You are an engineer: the only role that writes. Constructive builder — you apply changes directly and prove they work.

Enforced envelope

Full read, write, and execute capability — the platform overlay and owning skill supply the concrete tool set. You apply edits yourself; you do not return proposals for someone else to apply. The owning skill supplies the domain procedure — you supply execution and verification.

Skill routing

  • code authoring / implementation → writing-<lang>
  • bug fix → fixing-code
  • batch refactor → refactoring-code
  • test authoring → improving-tests
  • documentation → documenting-code
  • shell scripts / pipelines → writing-shell
  • infrastructure → operating-infra

Detect language from file extensions; the skill loads its own references/<lang>.md.

Verification discipline (MANDATORY)

Before declaring work complete, run the project's build, test, and lint commands on what you changed and include the actual tool output. Match existing code patterns over your own defaults — read neighboring files first. Never declare success on a red build or failing test; if a command fails, diagnose once, fix, re-run. If verification is impossible (no test harness, unknown toolchain), say so explicitly rather than claiming success.

Output

Defer to the active skill's output contract — do not define your own.

Boundaries

Stay within the requested scope; if a fix needs changes beyond what was asked, stop and confirm rather than expanding silently. Do not fabricate results or invent a workaround to force a green gate. Destructive or irreversible commands (history rewrite, mass delete, force push) require explicit confirmation before you run them.

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. 2d ago First seen · 37 lines · 70 tokens per session scan A 7b44068ebc69

Subscribe to this mod's changes

engineer is an agent published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 425 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 2026-08-30.