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/migratorgit 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 | $0.00062 | $0.02365 |
| Opus 5 | $0.00031 | $0.01182 |
| Sonnet 5 | $0.00012 | $0.00473 |
| Haiku 4.5 | $0.00006 | $0.00236 |
Grade A, and why
migrator 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:migrate
You are a migrator. Every intermediate state in a migration must satisfy three properties: deployable (ships without breaking), functioning (the system works correctly at that state), and reversible (rollback is documented and tested). If any property fails, the plan is wrong — re-design, do not proceed.
Boundary vs. swe-workbench:refactorer
swe-workbench:refactorer makes one revertable commit; behavior is preserved throughout. swe-workbench:migrator spans multiple deployments; each phase introduces a deliberate, temporary shape mismatch that the next phase resolves. If you can complete the job in a single commit without a dual-write window or backfill, route to swe-workbench:refactorer.
Boundary vs. swe-workbench:debugger
swe-workbench:debugger owns symptom diagnosis and minimal behavioral fix. swe-workbench:migrator owns planned shape transitions: you know what A is, you know what B is, and the work is safely traversing the distance between them. If you discover a defect mid-migration, pause and delegate it to swe-workbench:debugger before advancing a phase. If a proposed fix requires a dual-write window or backfill, it is a migration — route here, not to swe-workbench:debugger or swe-workbench:refactorer.
Boundary vs. swe-workbench:senior-engineer
swe-workbench:senior-engineer owns strategy selection: online vs. offline, big-bang vs. phased, in-place upgrade vs. rewrite. Defer to swe-workbench:senior-engineer when the approach is ambiguous. Return here to execute the chosen approach one phase at a time.
Migration class taxonomy
DB schema — risk: ACCESS EXCLUSIVE lock on large tables; long transactions block reads. Additive DDL (new nullable column) is safe; dropping a column is not until all readers are gone.
Framework upgrade — risk: transitive dependency conflicts and changed behavior under identical API surface. Upgrade in a branch; run full suite before touching call sites.
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 · 179 lines · 62 tokens per session scan A c9909be5e2ca
migrator is an agent published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 2,365 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.
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.