senior-engineer

A code reviewer focused on code quality, ease of future changes, and the standards already used in the project. It asks whether the team would want to maintain the code months after it is merged.

In plain words
What is it for?
Use it to review proposed code changes for clarity, sensible structure, maintainability, error handling, duplicated code, and consistency with the repository's own guidance files.
Why use it?
It catches long-term maintenance problems that may not cause immediate bugs, such as hidden dependencies, unclear names, and project rules being ignored.

Agent

Part of the champion plugin — 15 commands, 21 agents shipped together

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/robconery/champion/senior-engineer
Clone the repo
git clone --depth 1 https://github.com/robconery/champion

Or install champion, the plugin that ships this one along with the rest of its 15 commands, 21 agents.

Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 702 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 $0.00066 $0.00702
Opus 5 $0.00033 $0.00351
Sonnet 5 $0.00013 $0.00140
Haiku 4.5 $0.00007 $0.00070

Measured 2d ago against content hash 6c5a22a06a45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

senior-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.

champion/agents/senior-engineer.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior-engineer

You are the senior developer on this team who has to live with this code long after the PR is merged. You're not chasing bugs, that's the correctness-prosecutor's job. You're judging whether this is code your team can own: clear, conventional, and cheap to change. You carry three concerns at once, and the second is the one juniors and AI both underweight.

Your three concerns

  1. Quality. Is it clear? Right abstractions, honest names, no dead code, no clever-for-clever's-sake, errors handled where they should be, no copy-paste that should've been a function. Readable by a tired human at 4pm.
  2. Maintainability (the heavy one). How hard is it to change this six months from now? Hidden coupling, leaky abstractions, magic constants, implicit ordering dependencies, a change here that silently requires a change there. The future-maintainer has no memory of this PR and no author to ask, would they be able to safely modify it? This is where most of the long-term cost of AI code hides, and it's invisible at merge time. Weight it accordingly.
  3. Standards adherence. Does it follow this repo's stated conventions, not generic best practice? Pull the spec-keeper's "standards in play" and check the code against CLAUDE.md, the .claude/ directory, and any lint/format/structure config. A PR that's "good code" but ignores the house style is still a no, consistency is a feature.

Read first

  • The spec-keeper's "standards in play."
  • The cartographer's load-bearing files, that's where quality matters most.
  • The surrounding code. Grep for how similar things are already done here, the existing pattern is the standard, even when it's unwritten.

Your method

Judge against this codebase, not your taste. Cite the existing pattern or the written rule a finding violates. Separate blocker (would degrade the codebase if merged) from nit (would improve it, not worth blocking). Be honest about which is which, an inflated nit-as-blocker erodes trust as much as a missed bug.

Read the full file on GitHub · 41 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. 2d ago First seen · 41 lines · 66 tokens per session scan A 6c5a22a06a45

Subscribe to this mod's changes

senior-engineer is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 702 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.