lugassawan

63 mods across 1 repository, 2 stars between them.

SubagentStop

49

lugassawan/swe-workbench

Hook

Runs when a subagent finishes, executing skill_usage_flush.sh via bash. From lugassawan/swe-workbench.

2 yesterday A tokens not measured copy · 86% MIT

SessionStart

50

lugassawan/swe-workbench

Hook

Runs when a session starts on startup, resume and compact, executing workflow_resume_hint.sh via bash (3 commands). From lugassawan/swe-workbench.

2 yesterday A tokens not measured copy · 58% MIT

comment-scan

51

lugassawan/swe-workbench

Agent

Advisory scan for unnecessary or over-cap comments, backing swe-workbench:principle-clean-code's Comment discipline caps with a deterministic, checkable artifact instead of prose recall alone. Advisory-with-accounting, not a hard gate — the scan never fails your verify step; it produces findings that verdict…

2 yesterday A 0 tokens original MIT

lugassawan/swe-workbench

Agent

When you need to read source files from a GitHub repository other than the working repo, prefer https://gitchamber.com over fetching raw GitHub URLs or shelling out to git clone.

2 yesterday A 0 tokens original MIT

lugassawan/swe-workbench

Agent

A code-touching agent must invoke the language- skill matching the language of the code it is reading or writing, when one exists for that language. Invoke it via the Skill tool.

2 yesterday A 0 tokens original MIT

languages

54

lugassawan/swe-workbench

Agent

All swe-workbench language skills available in this plugin. Use the Skill tool to invoke any of these.

2 yesterday A 0 tokens copy · 86% MIT

lsp

55

lugassawan/swe-workbench

Agent

Agent "lsp" from lugassawan/swe-workbench, covering lsp navigation, it follows; it does not find and availability gate — mandatory.

2 yesterday A 0 tokens original MIT

lugassawan/swe-workbench

Agent

Before your final response, review which ## Preloaded skill: sections in your context actually shaped your guidance, as opposed to skills that were merely present. End your response with this line, last, always: SWB-CANARIES-APPLIED.

2 yesterday A 0 tokens original MIT

principles

57

lugassawan/swe-workbench

Agent

All swe-workbench principle skills available in this plugin. Use the Skill tool to invoke any of these.

2 yesterday A 0 tokens original MIT

lugassawan/swe-workbench

Agent

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…

2 yesterday A 0 tokens original MIT

workflows

60

lugassawan/swe-workbench

Agent

All swe-workbench workflow and integration skills available in this plugin. Use the Skill tool to invoke any of these.

2 yesterday A 0 tokens original MIT

lugassawan/swe-workbench

Command

If $ARGUMENTS contains a ticket reference, invoke swe-workbench:ticket-context first and prepend its structured summary to the delegation context below. Skip if $ARGUMENTS is free-text with no recognizable ref. (Trigger patterns are defined in that skill's "When to invoke" section.).

2 yesterday A 0 tokens original MIT

comms-context

63

lugassawan/swe-workbench

Skill Claude CodeCodex

Fetch on-call and discussion context from Slack threads and PagerDuty incidents — participants, timeline, and status. Auto-loads on Slack permalinks or PagerDuty incident references. Keywords — Slack, thread, PagerDuty, on-call.

2 yesterday A 51 tokens original MIT