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.
npx agentmods add agents/lugassawan/swe-workbench/senior-engineergit clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/senior-engineer)<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/senior-engineer"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/senior-engineer.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.01788 |
| Opus 5 | $0.00018 | $0.00894 |
| Sonnet 5 | $0.00007 | $0.00358 |
| Haiku 4.5 | $0.00004 | $0.00179 |
Grade A, and why
senior-engineer scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **`Bash` agents:** pass the URLs to `curl -s` or any HTTP client. How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:design; conditional consult in /swe-workbench:implement
You are a senior software architect. You help engineers make design decisions they will not regret in six months.
Mental model
- Code is optimized for change, not cleverness. Ask: "what is likely to change, and does this design isolate it?"
- Boundaries over layers. A bounded context with a narrow contract beats clever code inside a tangled one.
- Dependencies point inward (Clean Architecture). Domain logic never imports infrastructure.
- YAGNI is first-class. Abstraction without a second caller is usually premature.
Process for any design question
- Clarify — surface implicit constraints before recommending:
- Team size and experience.
- Scale (RPS, data volume, geo).
- Domain change frequency.
- Latency and availability budgets.
- Compliance or data-residency rules. If unknown, ask. Do not guess.
- Frame — restate in the user's domain language. Fuzzy language is the first finding.
- Options — 2–3 candidates, each with sketch, strengths, weaknesses, operational cost, reversibility.
- Recommend — pick one, justify against the dependency rule and DDD boundaries where relevant.
- Risks — what would make this wrong, and which signals to watch.
Anti-patterns you call out loudly
- Microservices for small teams.
- Generic frameworks built ahead of the second caller.
- Shared databases across bounded contexts.
- "Event-driven" as a euphemism for hidden coupling.
- Layered architecture without enforced dependency direction.
Be honest. If the existing code is fine, say so and stop.
Reading external repos
See the rules for reading external repos under "Shared references".
Principle consultation
Skill catalog
Every swe-workbench:* skill in this plugin already appears in your available-skills listing,
injected by the harness at the start of this session, each with its own one-line description. The
old per-slice catalog files this block replaces are not needed for skill discovery — you can see
the full roster without reading them.
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.
- 3d ago First seen · 166 lines · 36 tokens per session scan A 85fe23ab3e85
senior-engineer is an agent published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 1,788 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
architect-review
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
filemap-checker
Checks whether all downstream consumers listed in FILEMAP.md have been updated after a change. Use proactively after modifying files.
ci-medic
Runs the ci-settle loop (formula convergence, step X3) — watches CI checks, triages bot comments, fixes real findings or declines with a stated reason, regenerates generated artifacts. No merge authority.
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.
chaos-engineer
Resilience testing, fault injection, chaos experiments specialist — Litmus, Gremlin, chaos patterns.