@bradygaster/squad-sdk 0.9.0 → 0.9.1

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 (76) hide show
  1. package/README.md +296 -296
  2. package/dist/agents/history-shadow.js +30 -30
  3. package/dist/build/github-dist.js +42 -42
  4. package/dist/config/init.js +173 -173
  5. package/dist/sharing/consult.js +78 -78
  6. package/package.json +1 -1
  7. package/templates/casting/Futurama.json +9 -9
  8. package/templates/casting-history.json +4 -4
  9. package/templates/casting-policy.json +37 -37
  10. package/templates/casting-reference.md +104 -104
  11. package/templates/casting-registry.json +3 -3
  12. package/templates/ceremonies.md +41 -41
  13. package/templates/charter.md +53 -53
  14. package/templates/constraint-tracking.md +38 -38
  15. package/templates/cooperative-rate-limiting.md +229 -229
  16. package/templates/copilot-instructions.md +46 -46
  17. package/templates/history.md +10 -10
  18. package/templates/identity/now.md +9 -9
  19. package/templates/identity/wisdom.md +15 -15
  20. package/templates/issue-lifecycle.md +412 -412
  21. package/templates/keda-scaler.md +164 -164
  22. package/templates/machine-capabilities.md +74 -74
  23. package/templates/mcp-config.md +90 -90
  24. package/templates/multi-agent-format.md +28 -28
  25. package/templates/plugin-marketplace.md +49 -49
  26. package/templates/ralph-circuit-breaker.md +313 -313
  27. package/templates/raw-agent-output.md +37 -37
  28. package/templates/roster.md +60 -60
  29. package/templates/routing.md +39 -39
  30. package/templates/run-output.md +50 -50
  31. package/templates/schedule.json +19 -19
  32. package/templates/scribe-charter.md +119 -119
  33. package/templates/skill.md +24 -24
  34. package/templates/skills/agent-collaboration/SKILL.md +42 -42
  35. package/templates/skills/agent-conduct/SKILL.md +24 -24
  36. package/templates/skills/architectural-proposals/SKILL.md +151 -151
  37. package/templates/skills/ci-validation-gates/SKILL.md +84 -84
  38. package/templates/skills/cli-wiring/SKILL.md +47 -47
  39. package/templates/skills/client-compatibility/SKILL.md +89 -89
  40. package/templates/skills/cross-squad/SKILL.md +114 -114
  41. package/templates/skills/distributed-mesh/SKILL.md +287 -287
  42. package/templates/skills/distributed-mesh/mesh.json.example +30 -30
  43. package/templates/skills/distributed-mesh/sync-mesh.ps1 +111 -111
  44. package/templates/skills/distributed-mesh/sync-mesh.sh +104 -104
  45. package/templates/skills/docs-standards/SKILL.md +71 -71
  46. package/templates/skills/economy-mode/SKILL.md +114 -114
  47. package/templates/skills/external-comms/SKILL.md +329 -329
  48. package/templates/skills/gh-auth-isolation/SKILL.md +183 -183
  49. package/templates/skills/git-workflow/SKILL.md +204 -204
  50. package/templates/skills/github-multi-account/SKILL.md +95 -95
  51. package/templates/skills/history-hygiene/SKILL.md +36 -36
  52. package/templates/skills/humanizer/SKILL.md +105 -105
  53. package/templates/skills/init-mode/SKILL.md +102 -102
  54. package/templates/skills/model-selection/SKILL.md +117 -117
  55. package/templates/skills/nap/SKILL.md +24 -24
  56. package/templates/skills/personal-squad/SKILL.md +57 -57
  57. package/templates/skills/project-conventions/SKILL.md +56 -56
  58. package/templates/skills/release-process/SKILL.md +423 -423
  59. package/templates/skills/reskill/SKILL.md +92 -92
  60. package/templates/skills/reviewer-protocol/SKILL.md +79 -79
  61. package/templates/skills/secret-handling/SKILL.md +200 -200
  62. package/templates/skills/session-recovery/SKILL.md +155 -155
  63. package/templates/skills/squad-conventions/SKILL.md +69 -69
  64. package/templates/skills/test-discipline/SKILL.md +37 -37
  65. package/templates/skills/windows-compatibility/SKILL.md +74 -74
  66. package/templates/workflows/squad-ci.yml +24 -24
  67. package/templates/workflows/squad-docs.yml +54 -54
  68. package/templates/workflows/squad-heartbeat.yml +171 -171
  69. package/templates/workflows/squad-insider-release.yml +61 -61
  70. package/templates/workflows/squad-issue-assign.yml +161 -161
  71. package/templates/workflows/squad-label-enforce.yml +181 -181
  72. package/templates/workflows/squad-preview.yml +55 -55
  73. package/templates/workflows/squad-promote.yml +120 -120
  74. package/templates/workflows/squad-release.yml +77 -77
  75. package/templates/workflows/squad-triage.yml +260 -260
  76. package/templates/workflows/sync-squad-labels.yml +169 -169
@@ -1,114 +1,114 @@
1
- ---
2
- name: "economy-mode"
3
- description: "Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active."
4
- domain: "model-selection"
5
- confidence: "low"
6
- source: "manual"
7
- ---
8
-
9
- ## SCOPE
10
-
11
- ✅ THIS SKILL PRODUCES:
12
- - A modified Layer 3 model selection table applied when economy mode is active
13
- - `economyMode: true` written to `.squad/config.json` when activated persistently
14
- - Spawn acknowledgments with `💰` indicator when economy mode is active
15
-
16
- ❌ THIS SKILL DOES NOT PRODUCE:
17
- - Code, tests, or documentation
18
- - Cost reports or billing artifacts
19
- - Changes to Layer 0, Layer 1, or Layer 2 resolution (user intent always wins)
20
-
21
- ## Context
22
-
23
- Economy mode shifts Layer 3 (Task-Aware Auto-Selection) to lower-cost alternatives. It does NOT override persistent config (`defaultModel`, `agentModelOverrides`) or per-agent charter preferences — those represent explicit user intent and always take priority.
24
-
25
- Use this skill when the user wants to reduce costs across an entire session or permanently, without manually specifying models for each agent.
26
-
27
- ## Activation Methods
28
-
29
- | Method | How |
30
- |--------|-----|
31
- | Session phrase | "use economy mode", "save costs", "go cheap", "reduce costs" |
32
- | Persistent config | `"economyMode": true` in `.squad/config.json` |
33
- | CLI flag | `squad --economy` |
34
-
35
- **Deactivation:** "turn off economy mode", "disable economy mode", or remove `economyMode` from `config.json`.
36
-
37
- ## Economy Model Selection Table
38
-
39
- When economy mode is **active**, Layer 3 auto-selection uses this table instead of the normal defaults:
40
-
41
- | Task Output | Normal Mode | Economy Mode |
42
- |-------------|-------------|--------------|
43
- | Writing code (implementation, refactoring, bug fixes) | `claude-sonnet-4.5` | `gpt-4.1` or `gpt-5-mini` |
44
- | Writing prompts or agent designs | `claude-sonnet-4.5` | `gpt-4.1` or `gpt-5-mini` |
45
- | Docs, planning, triage, changelogs, mechanical ops | `claude-haiku-4.5` | `gpt-4.1` or `gpt-5-mini` |
46
- | Architecture, code review, security audits | `claude-opus-4.5` | `claude-sonnet-4.5` |
47
- | Scribe / logger / mechanical file ops | `claude-haiku-4.5` | `gpt-4.1` |
48
-
49
- **Prefer `gpt-4.1` over `gpt-5-mini`** when the task involves structured output or agentic tool use. Prefer `gpt-5-mini` for pure text generation tasks where latency matters.
50
-
51
- ## AGENT WORKFLOW
52
-
53
- ### On Session Start
54
-
55
- 1. READ `.squad/config.json`
56
- 2. CHECK for `economyMode: true` — if present, activate economy mode for the session
57
- 3. STORE economy mode state in session context
58
-
59
- ### On User Phrase Trigger
60
-
61
- **Session-only (no config change):** "use economy mode", "save costs", "go cheap"
62
-
63
- 1. SET economy mode active for this session
64
- 2. ACKNOWLEDGE: `✅ Economy mode active — using cost-optimized models this session. (Layer 0 and Layer 2 preferences still apply)`
65
-
66
- **Persistent:** "always use economy mode", "save economy mode"
67
-
68
- 1. WRITE `economyMode: true` to `.squad/config.json` (merge, don't overwrite other fields)
69
- 2. ACKNOWLEDGE: `✅ Economy mode saved — cost-optimized models will be used until disabled.`
70
-
71
- ### On Every Agent Spawn (Economy Mode Active)
72
-
73
- 1. CHECK Layer 0a/0b first (agentModelOverrides, defaultModel) — if set, use that. Economy mode does NOT override Layer 0.
74
- 2. CHECK Layer 1 (session directive for a specific model) — if set, use that. Economy mode does NOT override explicit session directives.
75
- 3. CHECK Layer 2 (charter preference) — if set, use that. Economy mode does NOT override charter preferences.
76
- 4. APPLY economy table at Layer 3 instead of normal table.
77
- 5. INCLUDE `💰` in spawn acknowledgment: `🔧 {Name} ({model} · 💰 economy) — {task}`
78
-
79
- ### On Deactivation
80
-
81
- **Trigger phrases:** "turn off economy mode", "disable economy mode", "use normal models"
82
-
83
- 1. REMOVE `economyMode` from `.squad/config.json` (if it was persisted)
84
- 2. CLEAR session economy mode state
85
- 3. ACKNOWLEDGE: `✅ Economy mode disabled — returning to standard model selection.`
86
-
87
- ### STOP
88
-
89
- After updating economy mode state and including the `💰` indicator in spawn acknowledgments, this skill is done. Do NOT:
90
- - Change Layer 0, Layer 1, or Layer 2 model choices
91
- - Override charter-specified models
92
- - Generate cost reports or comparisons
93
- - Fall back to premium models via economy mode (economy mode never bumps UP)
94
-
95
- ## Config Schema
96
-
97
- `.squad/config.json` economy-related fields:
98
-
99
- ```json
100
- {
101
- "version": 1,
102
- "economyMode": true
103
- }
104
- ```
105
-
106
- - `economyMode` — when `true`, Layer 3 uses the economy table. Optional; absent = economy mode off.
107
- - Combines with `defaultModel` and `agentModelOverrides` — Layer 0 always wins.
108
-
109
- ## Anti-Patterns
110
-
111
- - **Don't override Layer 0 in economy mode.** If the user set `defaultModel: "claude-opus-4.6"`, they want quality. Economy mode only affects Layer 3 auto-selection.
112
- - **Don't silently apply economy mode.** Always acknowledge when activated or deactivated.
113
- - **Don't treat economy mode as permanent by default.** Session phrases activate session-only; only "always" or `config.json` persist it.
114
- - **Don't bump premium tasks down too far.** Architecture and security reviews shift from opus to sonnet in economy mode — they do NOT go to fast/cheap models.
1
+ ---
2
+ name: "economy-mode"
3
+ description: "Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active."
4
+ domain: "model-selection"
5
+ confidence: "low"
6
+ source: "manual"
7
+ ---
8
+
9
+ ## SCOPE
10
+
11
+ ✅ THIS SKILL PRODUCES:
12
+ - A modified Layer 3 model selection table applied when economy mode is active
13
+ - `economyMode: true` written to `.squad/config.json` when activated persistently
14
+ - Spawn acknowledgments with `💰` indicator when economy mode is active
15
+
16
+ ❌ THIS SKILL DOES NOT PRODUCE:
17
+ - Code, tests, or documentation
18
+ - Cost reports or billing artifacts
19
+ - Changes to Layer 0, Layer 1, or Layer 2 resolution (user intent always wins)
20
+
21
+ ## Context
22
+
23
+ Economy mode shifts Layer 3 (Task-Aware Auto-Selection) to lower-cost alternatives. It does NOT override persistent config (`defaultModel`, `agentModelOverrides`) or per-agent charter preferences — those represent explicit user intent and always take priority.
24
+
25
+ Use this skill when the user wants to reduce costs across an entire session or permanently, without manually specifying models for each agent.
26
+
27
+ ## Activation Methods
28
+
29
+ | Method | How |
30
+ |--------|-----|
31
+ | Session phrase | "use economy mode", "save costs", "go cheap", "reduce costs" |
32
+ | Persistent config | `"economyMode": true` in `.squad/config.json` |
33
+ | CLI flag | `squad --economy` |
34
+
35
+ **Deactivation:** "turn off economy mode", "disable economy mode", or remove `economyMode` from `config.json`.
36
+
37
+ ## Economy Model Selection Table
38
+
39
+ When economy mode is **active**, Layer 3 auto-selection uses this table instead of the normal defaults:
40
+
41
+ | Task Output | Normal Mode | Economy Mode |
42
+ |-------------|-------------|--------------|
43
+ | Writing code (implementation, refactoring, bug fixes) | `claude-sonnet-4.5` | `gpt-4.1` or `gpt-5-mini` |
44
+ | Writing prompts or agent designs | `claude-sonnet-4.5` | `gpt-4.1` or `gpt-5-mini` |
45
+ | Docs, planning, triage, changelogs, mechanical ops | `claude-haiku-4.5` | `gpt-4.1` or `gpt-5-mini` |
46
+ | Architecture, code review, security audits | `claude-opus-4.5` | `claude-sonnet-4.5` |
47
+ | Scribe / logger / mechanical file ops | `claude-haiku-4.5` | `gpt-4.1` |
48
+
49
+ **Prefer `gpt-4.1` over `gpt-5-mini`** when the task involves structured output or agentic tool use. Prefer `gpt-5-mini` for pure text generation tasks where latency matters.
50
+
51
+ ## AGENT WORKFLOW
52
+
53
+ ### On Session Start
54
+
55
+ 1. READ `.squad/config.json`
56
+ 2. CHECK for `economyMode: true` — if present, activate economy mode for the session
57
+ 3. STORE economy mode state in session context
58
+
59
+ ### On User Phrase Trigger
60
+
61
+ **Session-only (no config change):** "use economy mode", "save costs", "go cheap"
62
+
63
+ 1. SET economy mode active for this session
64
+ 2. ACKNOWLEDGE: `✅ Economy mode active — using cost-optimized models this session. (Layer 0 and Layer 2 preferences still apply)`
65
+
66
+ **Persistent:** "always use economy mode", "save economy mode"
67
+
68
+ 1. WRITE `economyMode: true` to `.squad/config.json` (merge, don't overwrite other fields)
69
+ 2. ACKNOWLEDGE: `✅ Economy mode saved — cost-optimized models will be used until disabled.`
70
+
71
+ ### On Every Agent Spawn (Economy Mode Active)
72
+
73
+ 1. CHECK Layer 0a/0b first (agentModelOverrides, defaultModel) — if set, use that. Economy mode does NOT override Layer 0.
74
+ 2. CHECK Layer 1 (session directive for a specific model) — if set, use that. Economy mode does NOT override explicit session directives.
75
+ 3. CHECK Layer 2 (charter preference) — if set, use that. Economy mode does NOT override charter preferences.
76
+ 4. APPLY economy table at Layer 3 instead of normal table.
77
+ 5. INCLUDE `💰` in spawn acknowledgment: `🔧 {Name} ({model} · 💰 economy) — {task}`
78
+
79
+ ### On Deactivation
80
+
81
+ **Trigger phrases:** "turn off economy mode", "disable economy mode", "use normal models"
82
+
83
+ 1. REMOVE `economyMode` from `.squad/config.json` (if it was persisted)
84
+ 2. CLEAR session economy mode state
85
+ 3. ACKNOWLEDGE: `✅ Economy mode disabled — returning to standard model selection.`
86
+
87
+ ### STOP
88
+
89
+ After updating economy mode state and including the `💰` indicator in spawn acknowledgments, this skill is done. Do NOT:
90
+ - Change Layer 0, Layer 1, or Layer 2 model choices
91
+ - Override charter-specified models
92
+ - Generate cost reports or comparisons
93
+ - Fall back to premium models via economy mode (economy mode never bumps UP)
94
+
95
+ ## Config Schema
96
+
97
+ `.squad/config.json` economy-related fields:
98
+
99
+ ```json
100
+ {
101
+ "version": 1,
102
+ "economyMode": true
103
+ }
104
+ ```
105
+
106
+ - `economyMode` — when `true`, Layer 3 uses the economy table. Optional; absent = economy mode off.
107
+ - Combines with `defaultModel` and `agentModelOverrides` — Layer 0 always wins.
108
+
109
+ ## Anti-Patterns
110
+
111
+ - **Don't override Layer 0 in economy mode.** If the user set `defaultModel: "claude-opus-4.6"`, they want quality. Economy mode only affects Layer 3 auto-selection.
112
+ - **Don't silently apply economy mode.** Always acknowledge when activated or deactivated.
113
+ - **Don't treat economy mode as permanent by default.** Session phrases activate session-only; only "always" or `config.json` persist it.
114
+ - **Don't bump premium tasks down too far.** Architecture and security reviews shift from opus to sonnet in economy mode — they do NOT go to fast/cheap models.