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/principlesgit clone --depth 1 https://github.com/lugassawan/swe-workbenchWhat 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 | $0.00000 | $0.01108 |
| Opus 5 | $0.00000 | $0.00554 |
| Sonnet 5 | $0.00000 | $0.00222 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
principles 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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Principle catalog
All swe-workbench principle skills available in this plugin. Use the Skill tool to invoke any of these.
swe-workbench:principle-accessibility— Accessibility: WCAG 2.2 AA, semantic HTML, ARIA, keyboard navigation, focus management, color contrast, screen-reader compatibility.swe-workbench:principle-api-design— API design: contract-first, versioning, idempotency, REST/RPC/event trade-offs.swe-workbench:principle-clean-architecture— Clean Architecture: dependency rule, ports and adapters, domain-centric layering.swe-workbench:principle-clean-code— Clean code: DRY, KISS, YAGNI, naming, function length, abstraction level.swe-workbench:principle-code-review— Code review: five-axis lens (correctness, security, design, tests, comment quality), confidence-based filtering, comment tone, nitpick filtering.swe-workbench:principle-communication— Communication & output discipline: terse "caveman" output mode (lite/full/ultra), drop filler/hedging, preserve code symbols and error strings verbatim, auto-clarity carve-out.swe-workbench:principle-concurrency— Concurrency: race conditions, deadlock, structured concurrency, cancellation, backpressure.swe-workbench:principle-cost-awareness— Cost awareness: FinOps mindset, egress, right-sizing, scale-to-zero, cost-per-request, storage tiers, observability cost.swe-workbench:principle-data-modeling— Data modeling: storage paradigm selection, normalization depth, indexing strategy, hot-key avoidance, schema evolution, query-first design, retention.swe-workbench:principle-ddd— Domain-Driven Design: bounded contexts, aggregates, ubiquitous language, domain events.swe-workbench:principle-design-patterns— Design patterns: GoF catalog — Strategy, Factory, Observer, Decorator, Adapter, and more.swe-workbench:principle-distributed-systems— Distributed systems: CAP/PACELC, consistency models, consensus, quorum, logical clocks, replication, delivery semantics.swe-workbench:principle-error-handling— Error handling: errors as values, classification, wrapping, retry, circuit breakers.swe-workbench:principle-event-driven— Event-driven architecture: event sourcing, CQRS, sagas, schema evolution, consumer groups, DLQ, idempotent handlers.swe-workbench:principle-i18n— Internationalization & localization: locale-aware formatting, time zones, plural rules, message catalogs, RTL layout, ISO 8601, currency.swe-workbench:principle-observability— Observability: logs vs metrics vs traces, structured logging, OpenTelemetry, SLI/SLO.swe-workbench:principle-performance— Performance: latency vs throughput, profile-before-optimize, Big-O, allocation pressure, data locality, N+1 queries.swe-workbench:principle-postmortem— Postmortem principles: blameless culture, root cause analysis (5 Whys, Fishbone/Ishikawa), incident document structure, action-item discipline, MTTD/MTTR metrics.swe-workbench:principle-refactoring— Refactoring discipline: Fowler's catalog, smell→move mapping, rule of three, characterization-tests-first, small behavior-preserving steps with green between.swe-workbench:principle-release-engineering— Release engineering: semver discipline, expand-contract for breaking changes, idempotent release automation, post-release verification, rollback planning, release-notes audience.swe-workbench:principle-resiliency— Resiliency: failure domains, bulkheads, graceful degradation, fail-fast vs fail-soft, health checks, blast radius containment, idempotency keys, safe retry, rate limiting, token bucket, backpressure, jitter.swe-workbench:principle-security— Security: trust boundaries, input validation, secrets handling, secure defaults, threat modeling.swe-workbench:principle-solid— SOLID principles: SRP, OCP, LSP, ISP, DIP — responsibility, coupling, abstractions.swe-workbench:principle-tdd— TDD: red-green-refactor, test-first, F.I.R.S.T., Arrange-Act-Assert.swe-workbench:principle-testing— Testing strategy: test pyramid, doubles taxonomy, coverage-vs-confidence, mutation testing, flaky-test triage, contract testing, fixtures and builders, property-based tests.swe-workbench:principle-version-control— Version control: atomic commits, commit-message quality, branching strategy, rebase vs merge, squash vs preserve, PR description quality.swe-workbench:principle-product-design— UX and product design: Nielsen's 10 usability heuristics, visual hierarchy, information architecture, interaction design patterns, design-system compliance, responsive design. Accessibility/WCAG →swe-workbench:principle-accessibility.
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.
- 2d ago First seen · 32 lines · 0 tokens per session scan A 3efed8b03e29
principles is an agent published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,108 tokens. 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.
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.
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
ux-designer
For website changes, owns the "spec" phase as a design spec — information architecture, wireframe/description of the change, interaction notes. Gate 1 approves design, not prose. Persona frontend-ux.
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.
react-reviewer
React 19.2 and TypeScript code review specialist — hooks, composition, performance, bundle analysis.