xtrm-tools 0.7.17 → 0.7.19

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (57) hide show
  1. package/.xtrm/config/hooks.json +2 -0
  2. package/.xtrm/config/instructions/agents-top.md +2 -1
  3. package/.xtrm/registry.json +429 -712
  4. package/.xtrm/skills/default/creating-service-skills/scripts/bootstrap.py +82 -156
  5. package/.xtrm/skills/default/creating-service-skills/scripts/scaffolder.py +73 -121
  6. package/.xtrm/skills/default/hook-development/references/patterns.md +1 -1
  7. package/.xtrm/skills/default/last30days/scripts/test-v1-vs-v2.sh +2 -2
  8. package/.xtrm/skills/default/planning/SKILL.md +75 -29
  9. package/.xtrm/skills/default/releasing/SKILL.md +163 -57
  10. package/.xtrm/skills/default/security-pipeline/SKILL.md +192 -0
  11. package/.xtrm/skills/default/security-pipeline/scripts/security-bootstrap.sh +294 -0
  12. package/.xtrm/skills/default/security-pipeline/templates/.githooks/pre-push.template +39 -0
  13. package/.xtrm/skills/default/security-pipeline/templates/.github/workflows/gitleaks.yml +33 -0
  14. package/.xtrm/skills/default/security-pipeline/templates/.github/workflows/osv-scanner.yml +33 -0
  15. package/.xtrm/skills/default/security-pipeline/templates/.github/workflows/semgrep.yml +41 -0
  16. package/.xtrm/skills/default/security-pipeline/templates/.gitleaks.toml +44 -0
  17. package/.xtrm/skills/default/security-pipeline/templates/.pre-commit-config.yaml +67 -0
  18. package/.xtrm/skills/default/security-pipeline/templates/.semgrepignore +46 -0
  19. package/.xtrm/skills/default/security-pipeline/templates/scripts/security-scan.sh +57 -0
  20. package/.xtrm/skills/default/security-pipeline/templates/scripts/semgrep-diff.sh +68 -0
  21. package/.xtrm/skills/default/session-close-report/SKILL.md +167 -6
  22. package/.xtrm/skills/default/sync-docs/SKILL.md +1 -1
  23. package/.xtrm/skills/default/update-xt/SKILL.md +270 -4
  24. package/.xtrm/skills/default/updating-service-skills/scripts/drift_detector.py +22 -0
  25. package/.xtrm/skills/default/using-script-specialists/SKILL.md +7 -5
  26. package/.xtrm/skills/default/using-specialists/SKILL.md +13 -12
  27. package/.xtrm/skills/default/using-specialists-auto/SKILL.md +137 -0
  28. package/.xtrm/skills/default/using-specialists-v2/SKILL.md +14 -21
  29. package/.xtrm/skills/default/using-specialists-v3/SKILL.md +533 -21
  30. package/.xtrm/skills/default/vaultctl/SKILL.md +2 -2
  31. package/CHANGELOG.md +87 -3
  32. package/cli/dist/index.cjs +12429 -3769
  33. package/cli/dist/index.cjs.map +1 -1
  34. package/cli/package.json +9 -3
  35. package/package.json +27 -7
  36. package/packages/pi-extensions/package.json +1 -1
  37. package/.xtrm/skills/default/planning/evals/evals.json +0 -19
  38. package/.xtrm/skills/default/quality-gates/evals/evals.json +0 -181
  39. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/FINAL-EVAL-SUMMARY.md +0 -75
  40. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/edge-case-auto-fix-verification/with_skill/outputs/response.md +0 -59
  41. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/edge-case-mixed-language-project/with_skill/outputs/response.md +0 -60
  42. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/eval-summary.md +0 -105
  43. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/partial-install-python-only/with_skill/outputs/response.md +0 -93
  44. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/python-refactor-request/with_skill/outputs/response.md +0 -104
  45. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/quality-gate-error-fix/with_skill/outputs/response.md +0 -74
  46. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/should-not-trigger-general-chat/with_skill/outputs/response.md +0 -18
  47. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/should-not-trigger-math-question/with_skill/outputs/response.md +0 -18
  48. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/should-not-trigger-unrelated-coding/with_skill/outputs/response.md +0 -56
  49. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/tdd-guard-blocking-confusion/with_skill/outputs/response.md +0 -67
  50. package/.xtrm/skills/default/quality-gates/workspace/iteration-1/typescript-feature-with-tests/with_skill/outputs/response.md +0 -97
  51. package/.xtrm/skills/default/sync-docs/evals/evals.json +0 -89
  52. package/.xtrm/skills/default/test-planning/evals/evals.json +0 -23
  53. package/.xtrm/skills/default/using-specialists/SKILL.safe.md +0 -1082
  54. package/.xtrm/skills/default/using-specialists/SKILL.ultra.md +0 -1082
  55. package/.xtrm/skills/default/using-specialists/evals/evals.json +0 -68
  56. package/.xtrm/skills/default/using-specialists-v3/evals/evals.json +0 -89
  57. package/packages/pi-extensions/.serena/project.yml +0 -130
@@ -1,68 +0,0 @@
1
- {
2
- "skill_name": "specialists-usage",
3
- "evals": [
4
- {
5
- "id": 1,
6
- "eval_name": "bug-investigation",
7
- "prompt": "I'm seeing intermittent failures where specialist jobs show status 'done' in `specialists feed` but `specialists result` says they're still running. Can you investigate what's causing this inconsistency in the job lifecycle?",
8
- "expected_output": "Agent delegates to a specialist (e.g. bug-hunt) rather than diving into the source code themselves. Should create a bead first, then run the specialist with --bead.",
9
- "assertions": [
10
- {
11
- "name": "invokes_specialist",
12
- "description": "Agent runs `specialists run` or calls use_specialist/start_specialist instead of reading source files directly"
13
- },
14
- {
15
- "name": "creates_bead_first",
16
- "description": "Agent creates a tracking bead before invoking the specialist"
17
- },
18
- {
19
- "name": "does_not_self_investigate",
20
- "description": "Agent does not read supervisor.ts, status.json, or other source files to investigate the bug themselves"
21
- }
22
- ],
23
- "files": []
24
- },
25
- {
26
- "id": 2,
27
- "eval_name": "code-review",
28
- "prompt": "The specialist runner module at src/specialist/runner.ts is the core execution layer. Can you review it for bugs, edge cases, and code quality issues? It's about 300 lines and fairly complex.",
29
- "expected_output": "Agent delegates to a specialist (e.g. parallel-review or codebase-explorer) rather than reading the file and writing a review themselves. Should create a bead first.",
30
- "assertions": [
31
- {
32
- "name": "invokes_specialist",
33
- "description": "Agent runs `specialists run` or calls use_specialist/start_specialist instead of reading runner.ts directly"
34
- },
35
- {
36
- "name": "creates_bead_first",
37
- "description": "Agent creates a tracking bead before invoking the specialist"
38
- },
39
- {
40
- "name": "does_not_self_review",
41
- "description": "Agent does not read runner.ts and write their own code review"
42
- }
43
- ],
44
- "files": []
45
- },
46
- {
47
- "id": 3,
48
- "eval_name": "test-coverage",
49
- "prompt": "src/specialist/loader.ts handles YAML file discovery and caching. Looking at the tests in tests/unit/specialist/loader.test.ts, what's missing? Can you add the coverage gaps?",
50
- "expected_output": "Agent delegates to a specialist (e.g. test-runner) rather than reading the files and writing tests themselves. Should create a bead first.",
51
- "assertions": [
52
- {
53
- "name": "invokes_specialist",
54
- "description": "Agent runs `specialists run` or calls use_specialist/start_specialist instead of writing tests directly"
55
- },
56
- {
57
- "name": "creates_bead_first",
58
- "description": "Agent creates a tracking bead before invoking the specialist"
59
- },
60
- {
61
- "name": "does_not_self_write_tests",
62
- "description": "Agent does not read loader.ts and loader.test.ts and write new test cases themselves"
63
- }
64
- ],
65
- "files": []
66
- }
67
- ]
68
- }
@@ -1,89 +0,0 @@
1
- {
2
- "skill_name": "using-specialists-v3",
3
- "evals": [
4
- {
5
- "id": 1,
6
- "eval_name": "role-selection-implementation",
7
- "prompt": "Need add one small feature in src/specialist/loader.ts, but I do not know exact path yet. Which specialist should handle discovery and implementation?",
8
- "expected_output": "Agent checks live registry if needed, creates/updates complete bead contracts, selects explorer for discovery then executor for implementation, and does not self-investigate substantial work.",
9
- "assertions": [
10
- {
11
- "name": "selects_specialist_role",
12
- "description": "Agent names a specialist role appropriate for unknown implementation work"
13
- },
14
- {
15
- "name": "uses_live_registry",
16
- "description": "Agent references specialists list --full instead of a static catalog"
17
- },
18
- {
19
- "name": "does_not_self_investigate",
20
- "description": "Agent does not read source files and solve it directly"
21
- }
22
- ],
23
- "files": []
24
- },
25
- {
26
- "id": 2,
27
- "eval_name": "role-selection-debugging",
28
- "prompt": "A specialist chain started failing with a stack trace and inconsistent result state. Who should inspect it, and what command surface should I use to check available flags?",
29
- "expected_output": "Agent selects debugger for root-cause analysis, may use test-runner for check execution, and points to sp help/subcommand help before relying on flags.",
30
- "assertions": [
31
- {
32
- "name": "selects_debugging_role",
33
- "description": "Agent chooses debugger or test-runner for failure analysis"
34
- },
35
- {
36
- "name": "uses_help_surface",
37
- "description": "Agent references sp help or subcommand help for command details"
38
- },
39
- {
40
- "name": "does_not_guess_flags",
41
- "description": "Agent does not invent CLI flags from memory"
42
- }
43
- ],
44
- "files": []
45
- },
46
- {
47
- "id": 3,
48
- "eval_name": "role-selection-review",
49
- "prompt": "Executor finished a change and I need final verification before merge. Which specialist next, and what should it check?",
50
- "expected_output": "Agent selects reviewer with its own bead and --job <exec-job>, checks bead contract plus diff, and treats PASS as merge gate.",
51
- "assertions": [
52
- {
53
- "name": "selects_reviewer_role",
54
- "description": "Agent chooses reviewer for post-implementation verification"
55
- },
56
- {
57
- "name": "checks_contract_and_diff",
58
- "description": "Agent states reviewer checks bead contract and diff"
59
- },
60
- {
61
- "name": "does_not_replace_reviewer_with_self",
62
- "description": "Agent does not perform the review directly"
63
- }
64
- ],
65
- "files": []
66
- },
67
- {
68
- "id": 4,
69
- "eval_name": "merge-publication-flow",
70
- "prompt": "Reviewer passed an executor chain. What should the orchestrator do next to publish the specialist work?",
71
- "expected_output": "Agent uses sp merge <chain-root-bead> for standalone chains or sp epic merge <epic-id> for epic-owned work, avoids manual git merge, and closes the bead only after required gates are confirmed.",
72
- "assertions": [
73
- {
74
- "name": "uses_specialist_merge",
75
- "description": "Agent names sp merge or sp epic merge as the publication path"
76
- },
77
- {
78
- "name": "avoids_manual_git_merge",
79
- "description": "Agent explicitly avoids manual git merge for specialist-owned work"
80
- },
81
- {
82
- "name": "honors_reviewer_gate",
83
- "description": "Agent publishes only after reviewer PASS or explicit operator acceptance"
84
- }
85
- ],
86
- "files": []
87
- }
88
- ]
89
- }
@@ -1,130 +0,0 @@
1
- # the name by which the project can be referenced within Serena
2
- project_name: "pi-extensions"
3
-
4
-
5
- # list of languages for which language servers are started; choose from:
6
- # al ansible bash clojure cpp
7
- # cpp_ccls crystal csharp csharp_omnisharp dart
8
- # elixir elm erlang fortran fsharp
9
- # go groovy haskell haxe hlsl
10
- # java json julia kotlin lean4
11
- # lua luau markdown matlab msl
12
- # nix ocaml pascal perl php
13
- # php_phpactor powershell python python_jedi python_ty
14
- # r rego ruby ruby_solargraph rust
15
- # scala solidity swift systemverilog terraform
16
- # toml typescript typescript_vts vue yaml
17
- # zig
18
- # (This list may be outdated. For the current list, see values of Language enum here:
19
- # https://github.com/oraios/serena/blob/main/src/solidlsp/ls_config.py
20
- # For some languages, there are alternative language servers, e.g. csharp_omnisharp, ruby_solargraph.)
21
- # Note:
22
- # - For C, use cpp
23
- # - For JavaScript, use typescript
24
- # - For Free Pascal/Lazarus, use pascal
25
- # Special requirements:
26
- # Some languages require additional setup/installations.
27
- # See here for details: https://oraios.github.io/serena/01-about/020_programming-languages.html#language-servers
28
- # When using multiple languages, the first language server that supports a given file will be used for that file.
29
- # The first language is the default language and the respective language server will be used as a fallback.
30
- # Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored.
31
- languages:
32
- - typescript
33
-
34
- # the encoding used by text files in the project
35
- # For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings
36
- encoding: "utf-8"
37
-
38
- # line ending convention to use when writing source files.
39
- # Possible values: unset (use global setting), "lf", "crlf", or "native" (platform default)
40
- # This does not affect Serena's own files (e.g. memories and configuration files), which always use native line endings.
41
- line_ending:
42
-
43
- # The language backend to use for this project.
44
- # If not set, the global setting from serena_config.yml is used.
45
- # Valid values: LSP, JetBrains
46
- # Note: the backend is fixed at startup. If a project with a different backend
47
- # is activated post-init, an error will be returned.
48
- language_backend:
49
-
50
- # whether to use project's .gitignore files to ignore files
51
- ignore_all_files_in_gitignore: true
52
-
53
- # advanced configuration option allowing to configure language server-specific options.
54
- # Maps the language key to the options.
55
- # Have a look at the docstring of the constructors of the LS implementations within solidlsp (e.g., for C# or PHP) to see which options are available.
56
- # No documentation on options means no options are available.
57
- ls_specific_settings: {}
58
-
59
- # list of additional paths to ignore in this project.
60
- # Same syntax as gitignore, so you can use * and **.
61
- # Note: global ignored_paths from serena_config.yml are also applied additively.
62
- ignored_paths: []
63
-
64
- # whether the project is in read-only mode
65
- # If set to true, all editing tools will be disabled and attempts to use them will result in an error
66
- # Added on 2025-04-18
67
- read_only: false
68
-
69
- # list of tool names to exclude.
70
- # This extends the existing exclusions (e.g. from the global configuration)
71
- # Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
72
- excluded_tools: []
73
-
74
- # list of tools to include that would otherwise be disabled (particularly optional tools that are disabled by default).
75
- # This extends the existing inclusions (e.g. from the global configuration).
76
- # Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
77
- included_optional_tools: []
78
-
79
- # fixed set of tools to use as the base tool set (if non-empty), replacing Serena's default set of tools.
80
- # This cannot be combined with non-empty excluded_tools or included_optional_tools.
81
- # Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
82
- fixed_tools: []
83
-
84
- # list of mode names that are to be activated by default, overriding the setting in the global configuration.
85
- # The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes.
86
- # If the setting is undefined/empty, the default_modes from the global configuration (serena_config.yml) apply.
87
- # Otherwise, this overrides the setting from the global configuration (serena_config.yml).
88
- # Therefore, you can set this to [] if you do not want the default modes defined in the global config to apply
89
- # for this project.
90
- # This setting can, in turn, be overridden by CLI parameters (--mode).
91
- # See https://oraios.github.io/serena/02-usage/050_configuration.html#modes
92
- default_modes:
93
-
94
- # list of mode names to be activated additionally for this project, e.g. ["query-projects"]
95
- # The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes.
96
- # See https://oraios.github.io/serena/02-usage/050_configuration.html#modes
97
- added_modes:
98
-
99
- # initial prompt for the project. It will always be given to the LLM upon activating the project
100
- # (contrary to the memories, which are loaded on demand).
101
- initial_prompt: ""
102
-
103
- # time budget (seconds) per tool call for the retrieval of additional symbol information
104
- # such as docstrings or parameter information.
105
- # This overrides the corresponding setting in the global configuration; see the documentation there.
106
- # If null or missing, use the setting from the global configuration.
107
- symbol_info_budget:
108
-
109
- # list of regex patterns which, when matched, mark a memory entry as read‑only.
110
- # Extends the list from the global configuration, merging the two lists.
111
- read_only_memory_patterns: []
112
-
113
- # list of regex patterns for memories to completely ignore.
114
- # Matching memories will not appear in list_memories or activate_project output
115
- # and cannot be accessed via read_memory or write_memory.
116
- # To access ignored memory files, use the read_file tool on the raw file path.
117
- # Extends the list from the global configuration, merging the two lists.
118
- # Example: ["_archive/.*", "_episodes/.*"]
119
- ignored_memory_patterns: []
120
-
121
- # list of additional workspace folder paths for cross-package reference support (e.g. in monorepos).
122
- # Paths can be absolute or relative to the project root.
123
- # Each folder is registered as an LSP workspace folder, enabling language servers to discover
124
- # symbols and references across package boundaries.
125
- # Currently supported for: TypeScript.
126
- # Example:
127
- # additional_workspace_folders:
128
- # - ../sibling-package
129
- # - ../shared-lib
130
- additional_workspace_folders: []