command-code 1.17.0 → 1.18.1
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.
- package/CHANGELOG.md +16 -0
- package/dist/bundled/command-code-knowledge/SKILL.md +10 -5
- package/dist/bundled/command-code-knowledge/reference/custom-agents.md +2 -2
- package/dist/bundled/command-code-knowledge/reference/custom-slash-commands.md +1 -1
- package/dist/bundled/command-code-knowledge/reference/headless.md +1 -1
- package/dist/bundled/command-code-knowledge/reference/hooks.md +1 -1
- package/dist/bundled/command-code-knowledge/reference/mcp.md +1 -1
- package/dist/bundled/command-code-knowledge/reference/memory.md +1 -1
- package/dist/bundled/command-code-knowledge/reference/models.md +68 -68
- package/dist/bundled/command-code-knowledge/reference/permissions.md +1 -1
- package/dist/bundled/command-code-knowledge/reference/plan-mode.md +1 -1
- package/dist/bundled/command-code-knowledge/reference/plans.md +16 -0
- package/dist/bundled/command-code-knowledge/reference/product-help.md +1 -1
- package/dist/bundled/command-code-knowledge/reference/sessions.md +1 -1
- package/dist/bundled/command-code-knowledge/reference/skills.md +1 -1
- package/dist/bundled/config/SKILL.md +18 -0
- package/dist/bundled/config/references/permissions.md +27 -0
- package/dist/bundled/config/references/settings.md +39 -0
- package/dist/bundled/mod-builder/reference/api.md +1 -1
- package/dist/bundled/mod-builder/reference/hooks-and-events.md +1 -1
- package/dist/bundled/mod-builder/reference/overview.md +1 -1
- package/dist/bundled/mod-builder/reference/packaging.md +1 -1
- package/dist/bundled/mod-builder/reference/ui.md +1 -1
- package/dist/bundled/mod-builder/reference/verify.md +1 -1
- package/dist/cli.mjs +5 -5
- package/package.json +4 -4
- package/vsix/commandcode-vscode.vsix +0 -0
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,17 @@
|
|
|
1
1
|
# command-code
|
|
2
2
|
|
|
3
|
+
## 1.18.1
|
|
4
|
+
|
|
5
|
+
### Patch Changes
|
|
6
|
+
|
|
7
|
+
- feat(knowledge): cache pricing, plans reference, and a headless plan answer (#3576)
|
|
8
|
+
|
|
9
|
+
## 1.18.0
|
|
10
|
+
|
|
11
|
+
### Minor Changes
|
|
12
|
+
|
|
13
|
+
- feat(tools): replace the config and knowledge tools with bundled skills #3560
|
|
14
|
+
|
|
3
15
|
## 1.17.0
|
|
4
16
|
|
|
5
17
|
### Minor Changes
|
|
@@ -17,6 +29,10 @@
|
|
|
17
29
|
- feat: background output reads can block for new output or exit and stream by offset
|
|
18
30
|
- feat: shell_output replaces bash_output, task_output, and monitor_events (old names keep working)
|
|
19
31
|
|
|
32
|
+
### Patch Changes
|
|
33
|
+
|
|
34
|
+
- fix: stream prior-agent session scans so a large Codex/Claude Code/Cursor history can't exhaust the heap at startup
|
|
35
|
+
|
|
20
36
|
## 1.15.1
|
|
21
37
|
|
|
22
38
|
### Patch Changes
|
|
@@ -16,12 +16,16 @@ the matching reference file.
|
|
|
16
16
|
|
|
17
17
|
1. Pick the reference file(s) below that cover the question and read them.
|
|
18
18
|
2. Answer from what they say; quote exact ids, flags, paths, and settings keys verbatim.
|
|
19
|
-
3. Model questions (which model, exact ids, context windows, efforts, prices
|
|
20
|
-
`reference/models.md` — ids there are EXACT; never invent a model id.
|
|
21
|
-
4.
|
|
19
|
+
3. Model questions (which model, exact ids, context windows, efforts, prices incl. cache
|
|
20
|
+
rates): read `reference/models.md` — ids there are EXACT; never invent a model id.
|
|
21
|
+
4. Account questions ("which plan am I on", "which models can/can't I use", credits,
|
|
22
|
+
limits): read `reference/plans.md` and the Min plan column in `reference/models.md`. The
|
|
23
|
+
plan itself is not readable headlessly — ask the user or point them at /usage. Never
|
|
24
|
+
dig through auth files, API endpoints, or TTY tricks.
|
|
25
|
+
5. Anything about the help surface (slash commands, keyboard shortcuts, CLI flags, taste,
|
|
22
26
|
FAQ, pricing links): `reference/product-help.md` — the same document the
|
|
23
|
-
|
|
24
|
-
|
|
27
|
+
bundled product-help reference.
|
|
28
|
+
6. Building a mod (a loadable ModApi plugin)? Switch to the `mod-builder` skill — it has
|
|
25
29
|
the mods reference and runnable examples.
|
|
26
30
|
|
|
27
31
|
## Reference index
|
|
@@ -38,6 +42,7 @@ the matching reference file.
|
|
|
38
42
|
- `reference/plan-mode.md` — Plan Mode
|
|
39
43
|
- `reference/sessions.md` — Sessions & Checkpoints
|
|
40
44
|
- `reference/models.md` — Command Code Models
|
|
45
|
+
- `reference/plans.md` — Plans, credits, and per-plan model access
|
|
41
46
|
- `reference/product-help.md` — Product help (slash commands, CLI, taste, FAQ, pricing)
|
|
42
47
|
<!-- generated:reference-index:end -->
|
|
43
48
|
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
<!--
|
|
1
|
+
<!-- Generated from the Command Code docs: https://commandcode.ai/docs -->
|
|
2
2
|
|
|
3
3
|
# Custom Agents
|
|
4
4
|
|
|
@@ -259,7 +259,7 @@ Common ids by category:
|
|
|
259
259
|
| Edit | `edit_file`, `write_file` |
|
|
260
260
|
| Execution | `shell_command`, `run_command`, `kill_shell` |
|
|
261
261
|
| Search | `web_search`, `web_fetch` |
|
|
262
|
-
| Other | `glob`, `todo_write`, `task_create`, `task_update`, `task_list`, `task_get`, `task_output`, `task_stop`, `cron_create`, `cron_list`, `cron_delete`, `get_diagnostics`, `
|
|
262
|
+
| Other | `glob`, `todo_write`, `task_create`, `task_update`, `task_list`, `task_get`, `task_output`, `task_stop`, `cron_create`, `cron_list`, `cron_delete`, `get_diagnostics`, `taste`, `ask_user_question`, `sleep`, `enter_plan_mode`, `exit_plan_mode`, `enter_worktree`, `exit_worktree` |
|
|
263
263
|
|
|
264
264
|
MCP tools go in by their raw name, e.g. `mcp__github__get_me`. The `agent` and `agent_output` tools can't be granted - that's what keeps delegation one level deep.
|
|
265
265
|
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
<!--
|
|
1
|
+
<!-- Generated from the Command Code docs: https://commandcode.ai/docs -->
|
|
2
2
|
|
|
3
3
|
# Command Code Models
|
|
4
4
|
|
|
@@ -6,83 +6,83 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
|
|
|
6
6
|
|
|
7
7
|
## Open Source
|
|
8
8
|
|
|
9
|
-
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out | Best for |
|
|
10
|
-
|
|
11
|
-
| `deepseek/deepseek-v4-pro` | DeepSeek V4 Pro | 1M | high, max | $0.435/$0.87 | hybrid-attention long-context reasoning |
|
|
12
|
-
| `deepseek/deepseek-v4-flash` | DeepSeek V4 Flash (latest) | 1M | high, max | $0.14/$0.28 | fast hybrid-attention reasoning |
|
|
13
|
-
| `moonshotai/Kimi-K3` | Kimi K3 | 1M | — | $3/$15 | long-horizon coding & knowledge work with 1M context |
|
|
14
|
-
| `moonshotai/Kimi-K2.7-Code` | Kimi K2.7 Code | 256K | — | $0.95/$4 | improved long-horizon coding with vision |
|
|
15
|
-
| `moonshotai/Kimi-K2.7-Code-Highspeed` | Kimi K2.7 Code HighSpeed | 262K | — | $1.9/$8 | high-speed long-horizon coding with vision |
|
|
16
|
-
| `moonshotai/Kimi-K2.6` | Kimi K2.6 | 256K | — | $0.95/$4 | long-horizon coding with vision |
|
|
17
|
-
| `moonshotai/Kimi-K2.5` | Kimi K2.5 | 256K | — | $0.6/$3 | multimodal frontend coding |
|
|
18
|
-
| `zai-org/GLM-5.2` | GLM-5.2 | 1M | high, max | $1.4/$4.4 | powerful coding with 1M context and long-horizon tasks |
|
|
19
|
-
| `zai-org/GLM-5.2-Fast` | GLM-5.2 Fast | 1M | — | $3/$10.25 | high-throughput GLM-5.2 with 1M context |
|
|
20
|
-
| `zai-org/GLM-5.1` | GLM-5.1 | — | — | $1.4/$4.4 | long-horizon autonomous coding agent |
|
|
21
|
-
| `zai-org/GLM-5` | GLM-5 | 200K | — | $1/$3.2 | multi-mode thinking & long-range planning |
|
|
22
|
-
| `MiniMaxAI/MiniMax-M3` | MiniMax M3 | 1M | — | $0.3/$1.2 | frontier coding, agents & native multimodality |
|
|
23
|
-
| `MiniMaxAI/MiniMax-M2.7` | MiniMax M2.7 | — | — | $0.3/$1.2 | end-to-end software engineering agent |
|
|
24
|
-
| `MiniMaxAI/MiniMax-M2.5` | MiniMax M2.5 | 200K | — | $0.3/$1.2 | cross-platform full-stack agentic dev |
|
|
25
|
-
| `xiaomi/mimo-v2.5-pro` | MiMo V2.5 Pro | 1M | — | $0.435/$0.87 | high-capability long-context agentic coding |
|
|
26
|
-
| `xiaomi/mimo-v2.5` | MiMo V2.5 | 1M | — | $0.14/$0.28 | efficient long-context agentic coding |
|
|
27
|
-
| `Qwen/Qwen3.8-Max` | Qwen 3.8 Max | 1M | low, medium, xhigh | $2/$6 | autonomous long-horizon coding & professional work |
|
|
28
|
-
| `Qwen/Qwen3.7-Max` | Qwen 3.7 Max | 1M | — | $2.5/$7.5 | frontier coding & long-horizon agent execution |
|
|
29
|
-
| `Qwen/Qwen3.7-Plus` | Qwen 3.7 Plus | 1M | — | $0.4/$1.6 | agentic coding & reasoning at lower cost |
|
|
30
|
-
| `Qwen/Qwen3.7-Flash` | Qwen 3.7 Flash | 1M | — | $0.03/$0.13 | fast low-cost agentic coding & reasoning |
|
|
31
|
-
| `Qwen/Qwen3.6-Max-Preview` | Qwen 3.6 Max Preview | — | — | $1.3/$7.8 | vibe coding & efficient agent execution |
|
|
32
|
-
| `Qwen/Qwen3.6-Plus` | Qwen 3.6 Plus | — | — | $0.5/$3 | agentic coding & reasoning |
|
|
33
|
-
| `stepfun/Step-3.7-Flash` | Step 3.7 Flash | 256K | — | $0.2/$1.15 | multimodal sparse-MoE reasoning |
|
|
34
|
-
| `stepfun/Step-3.5-Flash` | Step 3.5 Flash | 1M | — | $0.1/$0.3 | fast sparse-MoE agentic reasoning |
|
|
35
|
-
| `tencent/hy3-paid` | Tencent Hy3 | 262K | — | $0.14/$0.58 | sparse-MoE reasoning & agentic tool use |
|
|
36
|
-
| `nvidia/nemotron-3-ultra-550b-a55b` | Nemotron 3 Ultra | 1M | — | $0.6/$2.4 | open reasoning model for long-horizon autonomous agents |
|
|
37
|
-
| `thinkingmachines/inkling` | Inkling | 256K | — | $1/$4.05 | multimodal MoE reasoning |
|
|
38
|
-
| `thinkingmachines/inkling-small` | Inkling Small | 1M | — | $0.5/$1.2 | lightweight MoE reasoning at lower cost and latency |
|
|
39
|
-
| `poolside/laguna-s-2.1-free` | Laguna S 2.1 | 256K | — | $0/$0 | open-weight agentic coding and long-horizon work |
|
|
9
|
+
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
|
|
10
|
+
|---|---|---|---|---|---|---|
|
|
11
|
+
| `deepseek/deepseek-v4-pro` | DeepSeek V4 Pro | 1M | high, max | $0.435/$0.87 · cache $0.003625 | Go and above | hybrid-attention long-context reasoning |
|
|
12
|
+
| `deepseek/deepseek-v4-flash` | DeepSeek V4 Flash (latest) | 1M | high, max | $0.14/$0.28 · cache $0.0028 | Go and above | fast hybrid-attention reasoning |
|
|
13
|
+
| `moonshotai/Kimi-K3` | Kimi K3 | 1M | — | $3/$15 · cache $0.3 | Go and above | long-horizon coding & knowledge work with 1M context |
|
|
14
|
+
| `moonshotai/Kimi-K2.7-Code` | Kimi K2.7 Code | 256K | — | $0.95/$4 · cache $0.19 | Go and above | improved long-horizon coding with vision |
|
|
15
|
+
| `moonshotai/Kimi-K2.7-Code-Highspeed` | Kimi K2.7 Code HighSpeed | 262K | — | $1.9/$8 · cache $0.38 | Go and above | high-speed long-horizon coding with vision |
|
|
16
|
+
| `moonshotai/Kimi-K2.6` | Kimi K2.6 | 256K | — | $0.95/$4 · cache $0.16 | Go and above | long-horizon coding with vision |
|
|
17
|
+
| `moonshotai/Kimi-K2.5` | Kimi K2.5 | 256K | — | $0.6/$3 · cache $0.1 | Go and above | multimodal frontend coding |
|
|
18
|
+
| `zai-org/GLM-5.2` | GLM-5.2 | 1M | high, max | $1.4/$4.4 · cache $0.26 | Go and above | powerful coding with 1M context and long-horizon tasks |
|
|
19
|
+
| `zai-org/GLM-5.2-Fast` | GLM-5.2 Fast | 1M | — | $3/$10.25 · cache $0.5 | Go and above | high-throughput GLM-5.2 with 1M context |
|
|
20
|
+
| `zai-org/GLM-5.1` | GLM-5.1 | — | — | $1.4/$4.4 · cache $0.26 | Go and above | long-horizon autonomous coding agent |
|
|
21
|
+
| `zai-org/GLM-5` | GLM-5 | 200K | — | $1/$3.2 · cache $0.2 | Go and above | multi-mode thinking & long-range planning |
|
|
22
|
+
| `MiniMaxAI/MiniMax-M3` | MiniMax M3 | 1M | — | $0.3/$1.2 · cache $0.06 | Go and above | frontier coding, agents & native multimodality |
|
|
23
|
+
| `MiniMaxAI/MiniMax-M2.7` | MiniMax M2.7 | — | — | $0.3/$1.2 · cache $0.06 | Go and above | end-to-end software engineering agent |
|
|
24
|
+
| `MiniMaxAI/MiniMax-M2.5` | MiniMax M2.5 | 200K | — | $0.3/$1.2 · cache $0.03 | Go and above | cross-platform full-stack agentic dev |
|
|
25
|
+
| `xiaomi/mimo-v2.5-pro` | MiMo V2.5 Pro | 1M | — | $0.435/$0.87 · cache $0.0036 | Go and above | high-capability long-context agentic coding |
|
|
26
|
+
| `xiaomi/mimo-v2.5` | MiMo V2.5 | 1M | — | $0.14/$0.28 · cache $0.0028 | Go and above | efficient long-context agentic coding |
|
|
27
|
+
| `Qwen/Qwen3.8-Max` | Qwen 3.8 Max | 1M | low, medium, xhigh | $2/$6 · cache $0.25 (write $2.5) | Go and above | autonomous long-horizon coding & professional work |
|
|
28
|
+
| `Qwen/Qwen3.7-Max` | Qwen 3.7 Max | 1M | — | $2.5/$7.5 · cache $0.5 (write $3.13) | Go and above | frontier coding & long-horizon agent execution |
|
|
29
|
+
| `Qwen/Qwen3.7-Plus` | Qwen 3.7 Plus | 1M | — | $0.4/$1.6 · cache $0.08 (write $0.5) | Go and above | agentic coding & reasoning at lower cost |
|
|
30
|
+
| `Qwen/Qwen3.7-Flash` | Qwen 3.7 Flash | 1M | — | $0.03/$0.13 · cache $0.006 (write $0.038) | Go and above | fast low-cost agentic coding & reasoning |
|
|
31
|
+
| `Qwen/Qwen3.6-Max-Preview` | Qwen 3.6 Max Preview | — | — | $1.3/$7.8 · cache $0.26 (write $1.63) | Go and above | vibe coding & efficient agent execution |
|
|
32
|
+
| `Qwen/Qwen3.6-Plus` | Qwen 3.6 Plus | — | — | $0.5/$3 · cache $0.1 | Go and above | agentic coding & reasoning |
|
|
33
|
+
| `stepfun/Step-3.7-Flash` | Step 3.7 Flash | 256K | — | $0.2/$1.15 · cache $0.04 | Go and above | multimodal sparse-MoE reasoning |
|
|
34
|
+
| `stepfun/Step-3.5-Flash` | Step 3.5 Flash | 1M | — | $0.1/$0.3 · cache $0.02 | Go and above | fast sparse-MoE agentic reasoning |
|
|
35
|
+
| `tencent/hy3-paid` | Tencent Hy3 | 262K | — | $0.14/$0.58 · cache $0.035 | Go and above | sparse-MoE reasoning & agentic tool use |
|
|
36
|
+
| `nvidia/nemotron-3-ultra-550b-a55b` | Nemotron 3 Ultra | 1M | — | $0.6/$2.4 · cache $0.12 | Go and above | open reasoning model for long-horizon autonomous agents |
|
|
37
|
+
| `thinkingmachines/inkling` | Inkling | 256K | — | $1/$4.05 · cache $0.17 | Go and above | multimodal MoE reasoning |
|
|
38
|
+
| `thinkingmachines/inkling-small` | Inkling Small | 1M | — | $0.5/$1.2 · cache $0.1 | Go and above | lightweight MoE reasoning at lower cost and latency |
|
|
39
|
+
| `poolside/laguna-s-2.1-free` | Laguna S 2.1 | 256K | — | $0/$0 · cache $0 | Go and above | open-weight agentic coding and long-horizon work |
|
|
40
40
|
## Anthropic
|
|
41
41
|
|
|
42
|
-
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out | Best for |
|
|
43
|
-
|
|
44
|
-
| `claude-sonnet-5` | Claude Sonnet 5 | 1M | low, medium, high, xhigh, max | $2/$10 | best combo of speed & intelligence (recommended) |
|
|
45
|
-
| `claude-sonnet-4-6` | Claude Sonnet 4.6 | 1M | low, medium, high, xhigh, max | $3/$15 | prev Sonnet, still fast & capable |
|
|
46
|
-
| `claude-fable-5` | Claude Fable 5 | 1M | low, medium, high, xhigh, max | $10/$50 | most capable for demanding reasoning & long-horizon agents |
|
|
47
|
-
| `claude-opus-5` | Claude Opus 5 | 1M | low, medium, high, xhigh, max | $5/$25 | most intelligent Opus for agents and coding |
|
|
48
|
-
| `claude-opus-4-8` | Claude Opus 4.8 | 1M | low, medium, high, xhigh, max | $5/$25 | prev flagship, still strong for agents and coding |
|
|
49
|
-
| `claude-opus-4-7` | Claude Opus 4.7 | 1M | low, medium, high, xhigh, max | $5/$25 | older Opus, still strong for agents and coding |
|
|
50
|
-
| `claude-haiku-4-5-20251001` | Claude Haiku 4.5 | 200K | — | $1/$5 | fastest & most compact, great for quick tasks |
|
|
42
|
+
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
|
|
43
|
+
|---|---|---|---|---|---|---|
|
|
44
|
+
| `claude-sonnet-5` | Claude Sonnet 5 | 1M | low, medium, high, xhigh, max | $2/$10 · cache $0.2 (write $2.5) | Pro and above | best combo of speed & intelligence (recommended) |
|
|
45
|
+
| `claude-sonnet-4-6` | Claude Sonnet 4.6 | 1M | low, medium, high, xhigh, max | $3/$15 · cache $0.3 (write $3.75) | Pro and above | prev Sonnet, still fast & capable |
|
|
46
|
+
| `claude-fable-5` | Claude Fable 5 | 1M | low, medium, high, xhigh, max | $10/$50 · cache $1 (write $12.5) | Max | most capable for demanding reasoning & long-horizon agents |
|
|
47
|
+
| `claude-opus-5` | Claude Opus 5 | 1M | low, medium, high, xhigh, max | $5/$25 · cache $0.5 (write $6.25) | Max | most intelligent Opus for agents and coding |
|
|
48
|
+
| `claude-opus-4-8` | Claude Opus 4.8 | 1M | low, medium, high, xhigh, max | $5/$25 · cache $0.5 (write $6.25) | Max | prev flagship, still strong for agents and coding |
|
|
49
|
+
| `claude-opus-4-7` | Claude Opus 4.7 | 1M | low, medium, high, xhigh, max | $5/$25 · cache $0.5 (write $6.25) | Max | older Opus, still strong for agents and coding |
|
|
50
|
+
| `claude-haiku-4-5-20251001` | Claude Haiku 4.5 | 200K | — | $1/$5 · cache $0.1 (write $1.25) | Pro and above | fastest & most compact, great for quick tasks |
|
|
51
51
|
## OpenAI
|
|
52
52
|
|
|
53
|
-
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out | Best for |
|
|
54
|
-
|
|
55
|
-
| `gpt-5.6-sol` | GPT-5.6 Sol | 1.05M | low, medium, high, xhigh, max | $5/$30 | frontier model for complex professional work |
|
|
56
|
-
| `gpt-5.6-terra` | GPT-5.6 Terra | 1.05M | low, medium, high, xhigh, max | $1/$6 | balances intelligence and cost |
|
|
57
|
-
| `gpt-5.6-luna` | GPT-5.6 Luna | 1.05M | low, medium, high, xhigh, max | $0.1/$0.6 | optimized for cost-sensitive workloads |
|
|
58
|
-
| `gpt-5.5` | GPT-5.5 | — | low, medium, high, xhigh | $5/$30 | latest frontier model for general complex work |
|
|
59
|
-
| `gpt-5.4` | GPT-5.4 | 400K | low, medium, high, xhigh | $2.5/$15 | frontier model for general complex work |
|
|
60
|
-
| `gpt-5.3-codex` | GPT-5.3 Codex | 400K | low, medium, high, xhigh | $2/$8 | frontier coding model |
|
|
61
|
-
| `gpt-5.4-mini` | GPT-5.4 Mini | 400K | low, medium, high | $0.75/$4.5 | fast, cost-effective model for everyday tasks |
|
|
53
|
+
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
|
|
54
|
+
|---|---|---|---|---|---|---|
|
|
55
|
+
| `gpt-5.6-sol` | GPT-5.6 Sol | 1.05M | low, medium, high, xhigh, max | $5/$30 · cache $0.5 (write $6.25) | Pro and above | frontier model for complex professional work |
|
|
56
|
+
| `gpt-5.6-terra` | GPT-5.6 Terra | 1.05M | low, medium, high, xhigh, max | $1/$6 · cache $0.1 (write $1.25) | Pro and above | balances intelligence and cost |
|
|
57
|
+
| `gpt-5.6-luna` | GPT-5.6 Luna | 1.05M | low, medium, high, xhigh, max | $0.1/$0.6 · cache $0.01 (write $0.125) | Go and above | optimized for cost-sensitive workloads |
|
|
58
|
+
| `gpt-5.5` | GPT-5.5 | — | low, medium, high, xhigh | $5/$30 · cache $0.5 (write $0) | Pro and above | latest frontier model for general complex work |
|
|
59
|
+
| `gpt-5.4` | GPT-5.4 | 400K | low, medium, high, xhigh | $2.5/$15 · cache $0.25 (write $0) | Pro and above | frontier model for general complex work |
|
|
60
|
+
| `gpt-5.3-codex` | GPT-5.3 Codex | 400K | low, medium, high, xhigh | $2/$8 · cache $0.5 (write $0) | Pro and above | frontier coding model |
|
|
61
|
+
| `gpt-5.4-mini` | GPT-5.4 Mini | 400K | low, medium, high | $0.75/$4.5 · cache $0.075 (write $0) | Pro and above | fast, cost-effective model for everyday tasks |
|
|
62
62
|
## Google
|
|
63
63
|
|
|
64
|
-
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out | Best for |
|
|
65
|
-
|
|
66
|
-
| `google/gemini-3.6-flash` | Gemini 3.6 Flash | 1M | low, medium, high | $1.5/$7.5 | higher-quality coding & agentic workflows, fewer tokens |
|
|
67
|
-
| `google/gemini-3.5-flash` | Gemini 3.5 Flash | 1M | low, medium, high | $1.5/$9 | Pro-level coding proficiency, parallel agentic execution |
|
|
68
|
-
| `google/gemini-3.5-flash-lite` | Gemini 3.5 Flash Lite | 1M | low, medium, high | $0.3/$2.5 | upgraded agentic capabilities, ideal for subagents |
|
|
69
|
-
| `google/gemini-3.1-flash-lite` | Gemini 3.1 Flash Lite | 1M | low, medium, high | $0.25/$1.5 | high-volume workhorse model with implicit caching |
|
|
64
|
+
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
|
|
65
|
+
|---|---|---|---|---|---|---|
|
|
66
|
+
| `google/gemini-3.6-flash` | Gemini 3.6 Flash | 1M | low, medium, high | $1.5/$7.5 · cache $0.15 | Pro and above | higher-quality coding & agentic workflows, fewer tokens |
|
|
67
|
+
| `google/gemini-3.5-flash` | Gemini 3.5 Flash | 1M | low, medium, high | $1.5/$9 · cache $0.15 | Pro and above | Pro-level coding proficiency, parallel agentic execution |
|
|
68
|
+
| `google/gemini-3.5-flash-lite` | Gemini 3.5 Flash Lite | 1M | low, medium, high | $0.3/$2.5 · cache $0.03 | Pro and above | upgraded agentic capabilities, ideal for subagents |
|
|
69
|
+
| `google/gemini-3.1-flash-lite` | Gemini 3.1 Flash Lite | 1M | low, medium, high | $0.25/$1.5 · cache $0.03 | Pro and above | high-volume workhorse model with implicit caching |
|
|
70
70
|
## Sakana
|
|
71
71
|
|
|
72
|
-
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out | Best for |
|
|
73
|
-
|
|
74
|
-
| `sakana/fugu-ultra` | Fugu Ultra | 1M | high, xhigh | $5/$30 | multi-agent orchestration across frontier models |
|
|
72
|
+
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
|
|
73
|
+
|---|---|---|---|---|---|---|
|
|
74
|
+
| `sakana/fugu-ultra` | Fugu Ultra | 1M | high, xhigh | $5/$30 · cache $0.5 | Max | multi-agent orchestration across frontier models |
|
|
75
75
|
## Meta
|
|
76
76
|
|
|
77
|
-
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out | Best for |
|
|
78
|
-
|
|
79
|
-
| `meta/muse-spark-1.1` | Muse Spark 1.1 | 1.05M | — | $1.25/$4.25 | agentic performance, tool use, and computer use |
|
|
80
|
-
| `meta/muse-spark-1.2` | Muse Spark 1.2 | 1.05M | — | $1.25/$4.25 | coding-optimized for agentic workflows and large codebases |
|
|
81
|
-
| `meta/muse-spark-1.2-contributor` | Muse Spark 1.2 Contributor | 1.05M | — | $0.1/$0.2 | Muse Spark 1.2 at ~95% off |
|
|
77
|
+
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
|
|
78
|
+
|---|---|---|---|---|---|---|
|
|
79
|
+
| `meta/muse-spark-1.1` | Muse Spark 1.1 | 1.05M | — | $1.25/$4.25 · cache $0.15 | Pro and above | agentic performance, tool use, and computer use |
|
|
80
|
+
| `meta/muse-spark-1.2` | Muse Spark 1.2 | 1.05M | — | $1.25/$4.25 · cache $0.15 | GOAT and above | coding-optimized for agentic workflows and large codebases |
|
|
81
|
+
| `meta/muse-spark-1.2-contributor` | Muse Spark 1.2 Contributor | 1.05M | — | $0.1/$0.2 · cache $0.002 | Go and above | Muse Spark 1.2 at ~95% off |
|
|
82
82
|
## xAI
|
|
83
83
|
|
|
84
|
-
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out | Best for |
|
|
85
|
-
|
|
86
|
-
| `xai/grok-4.5` | Grok 4.5 | 500K | low, medium, high | $2/$6 | smartest model for coding, agentic tasks, knowledge work |
|
|
84
|
+
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
|
|
85
|
+
|---|---|---|---|---|---|---|
|
|
86
|
+
| `xai/grok-4.5` | Grok 4.5 | 500K | low, medium, high | $2/$6 · cache $0.5 | Go and above | smartest model for coding, agentic tasks, knowledge work |
|
|
87
87
|
|
|
88
|
-
Rates are the advertised price list resolved from the billing source of truth (promos are already baked in). Models without an effort column entry decide their own reasoning depth. Full pricing detail: https://commandcode.ai/docs/resources/pricing-limits
|
|
88
|
+
Rates are the advertised price list resolved from the billing source of truth (promos are already baked in): input / output / cache-read per 1M tokens, plus cache-write where the provider bills it. Min plan is the cheapest public plan that serves the model, ordered Go < GOAT < Pro < Max (see plans.md). Models without an effort column entry decide their own reasoning depth. Full pricing detail: https://commandcode.ai/docs/resources/pricing-limits
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
<!-- Generated from the Command Code docs: https://commandcode.ai/docs -->
|
|
2
|
+
|
|
3
|
+
# Command Code Plans
|
|
4
|
+
|
|
5
|
+
The user's plan is not readable headlessly: ask the user which plan they are on, or point them at the /usage overlay (interactive sessions) or https://commandcode.ai — never guess it from local files, auth tokens, or API probing.
|
|
6
|
+
|
|
7
|
+
Individual plans, cheapest first: **Go**, **GOAT**, **Pro**, **Max**. Prices, monthly credits, and what each includes are on the docs pages below — read them rather than quoting numbers from memory:
|
|
8
|
+
|
|
9
|
+
- Go: https://commandcode.ai/docs/plans/go
|
|
10
|
+
- GOAT: https://commandcode.ai/docs/plans/goat
|
|
11
|
+
- Pro: https://commandcode.ai/docs/plans/pro
|
|
12
|
+
- Max: https://commandcode.ai/docs/plans/max
|
|
13
|
+
- Pricing and limits: https://commandcode.ai/docs/resources/pricing-limits
|
|
14
|
+
- Usage limits: https://commandcode.ai/docs/resources/usage-limits
|
|
15
|
+
|
|
16
|
+
To answer "which models can I use / not use": once the plan is known, read the Min plan column in models.md — the cheapest public plan (Go < GOAT < Pro < Max) that serves each model; every higher plan includes it. A model whose Min plan sits above the user's plan is one they lack access to. Note the plan tiers gate by billing category, not open- vs closed-source: some closed models are served on Go/GOAT.
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
<!--
|
|
1
|
+
<!-- Generated from the Command Code docs: https://commandcode.ai/docs -->
|
|
2
2
|
|
|
3
3
|
# Command Code — Product Knowledge
|
|
4
4
|
|
|
@@ -0,0 +1,18 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: config
|
|
3
|
+
description: Inspect or change validated Command Code settings. Use when asked about configuration, current values, themes, permission defaults, feature models, taste learning, sharing defaults, or when a setting change would help complete the task.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Configuration
|
|
7
|
+
|
|
8
|
+
Use the deterministic CLI instead of editing settings files by hand.
|
|
9
|
+
|
|
10
|
+
1. Determine whether the request needs `list`, `get`, or `set`.
|
|
11
|
+
2. Read [settings.md](references/settings.md) for keys and value rules. Read [permissions.md](references/permissions.md) only for permission-related changes.
|
|
12
|
+
3. Run `cmd config list|get|set|default` through `shell_command` with `--json` when structured output helps. On Windows the binary is `cmdc` (bare `cmd` opens the Windows shell) — use `cmdc config ...` there.
|
|
13
|
+
4. For writes, choose the explicit `user` or `project` scope supported by the setting — the `scope` column in [settings.md](references/settings.md) says which one each takes. Never guess a scope.
|
|
14
|
+
5. Report the previous value, new value, and written scope.
|
|
15
|
+
|
|
16
|
+
A running session adopts the change at the start of its next round, so report the write as applied without claiming the live session already reloaded it.
|
|
17
|
+
|
|
18
|
+
Never hand-edit invalid JSON or invent a setting key.
|
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
<!-- Generated from the Command Code configuration registry. Docs: https://commandcode.ai/docs -->
|
|
2
|
+
|
|
3
|
+
# Permission settings
|
|
4
|
+
|
|
5
|
+
`permissions.defaultMode` controls the default tool permission mode and is stored in user scope.
|
|
6
|
+
|
|
7
|
+
Allowed values:
|
|
8
|
+
|
|
9
|
+
- `default`: ask when no existing rule decides
|
|
10
|
+
- `plan`: restrict the session to planning-safe tools
|
|
11
|
+
- `auto-accept`: accept ordinary tool requests while preserving policy denials
|
|
12
|
+
- `dont-ask`: deny requests that would otherwise need a prompt
|
|
13
|
+
|
|
14
|
+
The unrestricted bypass mode cannot be written through `cmd config` because it is not a
|
|
15
|
+
stored setting at all. Bypass is a per-launch flag the USER passes when starting Command
|
|
16
|
+
Code: `--yolo` (alias for `--dangerously-skip-permissions`) skips permission prompts for
|
|
17
|
+
that run only, e.g. `cmd --yolo` or `cmd --yolo -p "..."` for print mode, where shell
|
|
18
|
+
commands and file writes are otherwise refused. Never suggest making it the stored default;
|
|
19
|
+
when a denied action needs it, tell the user to relaunch with `--yolo` themselves.
|
|
20
|
+
|
|
21
|
+
```text
|
|
22
|
+
cmd config get permissions.defaultMode --scope user --json
|
|
23
|
+
cmd config set permissions.defaultMode plan --scope user --json
|
|
24
|
+
cmd config default permissions.defaultMode --json
|
|
25
|
+
```
|
|
26
|
+
|
|
27
|
+
A short-lived config command changes disk state and exits, so its result reports `liveSessionReloaded: false`. A running session re-reads the changed settings at the start of its next model round and adopts the new default then — no restart needed.
|
|
@@ -0,0 +1,39 @@
|
|
|
1
|
+
<!-- Generated from the Command Code configuration registry. Docs: https://commandcode.ai/docs -->
|
|
2
|
+
|
|
3
|
+
# Settings reference
|
|
4
|
+
|
|
5
|
+
The executable registry is authoritative. Run `cmd config list --scope effective --json` before changing a value.
|
|
6
|
+
|
|
7
|
+
| Key | Scope | Type | Values | Description |
|
|
8
|
+
| --- | --- | --- | --- | --- |
|
|
9
|
+
| `model` | user | string | known model id | The default main-loop model. A long-lived host may also apply the change to its current session. |
|
|
10
|
+
| `permissions.defaultMode` | user | enum | `default`, `plan`, `auto-accept`, `dont-ask` | Default permission mode for tool usage. A long-lived host may also apply the change to its current session. "bypass" cannot be set here. |
|
|
11
|
+
| `theme` | user | enum | `dark`, `light`, `auto` | Terminal color theme (same setting as /theme). Auto automatically detects your terminal background and uses light or dark to match. |
|
|
12
|
+
| `compact-mode` | user | enum | `default`, `fast` | Auto-compact aggressiveness when context fills up (same setting as /compact-mode). |
|
|
13
|
+
| `force-oauth` | user | boolean | `true`, `false` | Require OAuth login and block API-key authentication. |
|
|
14
|
+
| `tree-filter-mode` | user | enum | `default`, `no-tools`, `user-only`, `labeled-only`, `all` | Default filter when opening /tree. |
|
|
15
|
+
| `on-demand-tool-descriptions` | user | boolean | `true`, `false` | Explain shell commands on permission prompts only when you press ctrl+e (default). Turn off to generate every explanation upfront. |
|
|
16
|
+
| `image-vision` | user | enum | `ask`, `enabled`, `disabled` | Let a text-only model read attached images by describing them with the vision model ("Ask on first use" prompts the first time you attach an image). |
|
|
17
|
+
| `branch-summary-skip-prompt` | user | boolean | `true`, `false` | Never ask about summarizing when switching branches in /tree. |
|
|
18
|
+
| `default-export-format` | user | enum | `html`, `jsonl`, `md` | Format a bare /export (no format or path) writes — an explicit /export html\|jsonl\|md\|<path> always overrides. |
|
|
19
|
+
| `default-share-gist-format` | user | enum | `html`, `jsonl`, `md` | Format a bare /share gist (no format argument) posts — an explicit /share gist html\|jsonl\|md always overrides. |
|
|
20
|
+
| `taste-learning` | user | boolean | `true`, `false` | Learn your coding style from your sessions, user-wide (same setting as /taste). |
|
|
21
|
+
| `taste-learning-project` | project | enum | `inherit`, `enabled`, `disabled` | Learn your coding style from this project only (same setting as /taste). |
|
|
22
|
+
| `feature-model:titleGeneration` | user | enum | known model id or `default` | Names your sessions after the first exchange. Value: a model id, or "default" to reset to the curated default. |
|
|
23
|
+
| `feature-model:compaction` | user | enum | known model id or `default` | Summarizes long conversations when context fills up. Value: a model id, or "default" to reset to the curated default. |
|
|
24
|
+
| `feature-model:toolDescription` | user | enum | known model id or `default` | Writes the one-line command summaries on permission prompts. Value: a model id, or "default" to reset to the curated default. |
|
|
25
|
+
| `feature-model:tasteLearning` | user | enum | known model id or `default` | Learns your coding style from your sessions. Value: a model id, or "default" to reset to the curated default. |
|
|
26
|
+
| `feature-model:tasteOnboarding` | user | enum | known model id or `default` | Streams live observations during onboarding. Value: a model id, or "default" to reset to the curated default. |
|
|
27
|
+
| `feature-model:branchSummarization` | user | enum | known model id or `default` | Summarizes an abandoned branch when you jump away from it. Value: a model id, or "default" to reset to the curated default. |
|
|
28
|
+
| `feature-model:vision` | user | enum | known model id or `default` | Describes attached images so a text-only model can read them. Value: a model id, or "default" to reset to the curated default. |
|
|
29
|
+
|
|
30
|
+
Commands:
|
|
31
|
+
|
|
32
|
+
```text
|
|
33
|
+
cmd config list [--scope effective|user|project] [--json] # alias: cmd config ls
|
|
34
|
+
cmd config get <key> [--scope effective|user|project] [--json]
|
|
35
|
+
cmd config set <key> <value> --scope user|project [--json]
|
|
36
|
+
cmd config default <key> [--json] # reset to the built-in default
|
|
37
|
+
```
|
|
38
|
+
|
|
39
|
+
Values may be JSON scalars or plain strings. The command refuses unknown keys, invalid enum values, locked settings, invalid JSON files, and unsupported scopes. `default` writes the setting's built-in fallback value using the setting's own scope. On Windows the binary is `cmdc` (bare `cmd` opens the Windows shell): `cmdc config list`.
|