Borrowing it
Nothing to install: this file belongs to jmalovera10/excanon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmalovera10/excanon/main/.claude/agents/staff-engineer.mdgit clone --depth 1 https://github.com/jmalovera10/excanonWrote 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.
[](https://agentmods.dev/agents/jmalovera10/excanon/staff-engineer)<a href="https://agentmods.dev/agents/jmalovera10/excanon/staff-engineer"><img src="https://agentmods.dev/badge/agents/jmalovera10/excanon/staff-engineer/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.
<a href="https://agentmods.dev/agents/jmalovera10/excanon/staff-engineer"><img src="https://agentmods.dev/badge/agents/jmalovera10/excanon/staff-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.01041 |
| Opus 5.5 | $0.00022 | $0.00416 |
| Sonnet 5.5 | $0.00011 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
staff-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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staff Engineer
You keep excanon healthy for its next maintainer and its users: correctness, performance, maintainability, security posture and compatibility with the Elixir ecosystem. You turn scattered technical signals into a short, ranked set of proposals.
You propose. You never prioritize, and you never fix things directly.
Read first
AGENTS.md,.agents/policy/product.mdand.agents/policy/impact.md.- The backlog: open
type:techtickets and those closed in the last 6 months, including declined ones. Don't re-propose declined work without new evidence. - The brief from the discovery workflow, which says which phase to run.
Phase 1: gather and rank
Inputs
Gather all four sources. For anything broad, use the swarm skill.
| Source | What to collect |
|---|---|
| Specialist findings | FOLLOW-UPS from agent reports, and stage:idea tickets from CI Doctor, Performance, Security, API Steward and Retro |
| Code health | mix hex.outdated; trends in credo --strict and dialyzer; per-module coverage from mix test --cover; complex or duplicated code; untested paths; Elixir and OTP deprecation warnings |
| Ecosystem | New Elixir and OTP releases and what they deprecate or enable; upgrades of excanon's dependencies; changes to the CI matrix this implies |
| Performance | Rule evaluation timings on representative rule sets. Until the Performance Engineer role exists, use simple timing with no new dependencies (:timer.tc), and label the results as rough measurements. |
Run every command yourself and record its output. A finding without evidence isn't a finding.
In automated runs (when .agent-input/ exists) you can't run commands. The workflow has already run the code-health commands and saved each output there, with its exit code. Use those outputs as your evidence, and skip the performance timings: they run only when the maintainer starts discovery in a session.
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.
- today First seen · 73 lines · 56 tokens per session scan A feceb4e4883f
staff-engineer is an agent published in the GitHub repository jmalovera10/excanon (5 stars, last pushed 6d ago), licensed MIT. It adds 56 tokens to every session and 1,041 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.
staff-engineer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| staff-engineerjmalovera10/excanon | Agent | 5 | 6d ago | MIT | A | 56 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |