enigma-cli 1.6.3 → 1.6.4
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/README.md +38 -5
- package/assets/memory/AGENTS.md +22 -0
- package/assets/memory/CLAUDE.md +22 -0
- package/assets/skills/backend-policy/skill.json +1 -1
- package/assets/skills/ciphera-style-policy/skill.json +1 -1
- package/assets/skills/code-review-policy/skill.json +1 -1
- package/assets/skills/core-engineering-policy/skill.json +1 -1
- package/assets/skills/database-expert/skill.json +1 -1
- package/assets/skills/debugging-policy/skill.json +1 -1
- package/assets/skills/dependency-policy/skill.json +1 -1
- package/assets/skills/frontend-policy/skill.json +1 -1
- package/assets/skills/git-policy/skill.json +1 -1
- package/assets/skills/security-policy/skill.json +1 -1
- package/assets/skills/testing-policy/skill.json +1 -1
- package/assets/skills/validation-policy/skill.json +1 -1
- package/bin/checksums.json +4 -4
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -30,11 +30,6 @@ enigma check Integrity gate: verify skills are well-formed and sealed
|
|
|
30
30
|
enigma help | version
|
|
31
31
|
```
|
|
32
32
|
|
|
33
|
-
Everything is modular and opt-in via [`@clack/prompts`](https://github.com/bombshell-dev/clack):
|
|
34
|
-
the menu lets you enable or disable each feature, and `enigma security` lets you
|
|
35
|
-
toggle each protection. Nothing touches your git config unless you run
|
|
36
|
-
`enigma security` or accept its prompt.
|
|
37
|
-
|
|
38
33
|
## Agent skills
|
|
39
34
|
|
|
40
35
|
Skills are authored once and deployed to every selected agent (no per-agent
|
|
@@ -130,6 +125,44 @@ enigma config commit-emoji off -g # global (~/.enigma.json)
|
|
|
130
125
|
|
|
131
126
|
Precedence: built-in default (on) -> `~/.enigma.json` -> repo `.enigma.json`.
|
|
132
127
|
|
|
128
|
+
## Parallel sub-agents
|
|
129
|
+
|
|
130
|
+
The memory file always tells agents to break long or complex tasks into smaller
|
|
131
|
+
subtasks and complete them incrementally. The parallel part - delegating
|
|
132
|
+
independent subtasks to sub-agents that run at the same time to finish faster -
|
|
133
|
+
is opt-in, because spawning sub-agents multiplies token cost:
|
|
134
|
+
|
|
135
|
+
```bash
|
|
136
|
+
enigma config parallel-subagents on # add the parallel section to the memory file
|
|
137
|
+
enigma config parallel-subagents off # remove it (default)
|
|
138
|
+
enigma config parallel-subagents on -g # global (~/.enigma.json)
|
|
139
|
+
```
|
|
140
|
+
|
|
141
|
+
This toggle edits the deployed agent memory file (adds or removes the section),
|
|
142
|
+
so **restart Claude Code / Codex / OpenCode** after changing it for the new
|
|
143
|
+
session to pick it up. Subtask decomposition itself is always on and is never
|
|
144
|
+
removed.
|
|
145
|
+
|
|
146
|
+
## Token-efficient output
|
|
147
|
+
|
|
148
|
+
Optionally compress the agent's chat prose to cut output tokens while keeping
|
|
149
|
+
full technical accuracy (inspired by [caveman](https://github.com/JuliusBrussee/caveman)).
|
|
150
|
+
Chosen at install or via config; off by default:
|
|
151
|
+
|
|
152
|
+
```bash
|
|
153
|
+
enigma config output-style lite # professional terse (drop filler, keep grammar)
|
|
154
|
+
enigma config output-style full # caveman-style fragments
|
|
155
|
+
enigma config output-style ultra # telegraphic, maximum compression
|
|
156
|
+
enigma config output-style off # back to full prose (default)
|
|
157
|
+
enigma install --output-style lite # set it during install
|
|
158
|
+
```
|
|
159
|
+
|
|
160
|
+
`on`/`off` also work (`on` = `lite`). Like the toggle above it edits the memory
|
|
161
|
+
file, so **restart your agent** after changing it. Code, comments, commits, and
|
|
162
|
+
PRs stay normal, the agent reverts to full prose for security warnings and other
|
|
163
|
+
safety-critical replies, and the level is switchable mid-session by asking
|
|
164
|
+
("be more terse", "ultra", "normal mode").
|
|
165
|
+
|
|
133
166
|
## License
|
|
134
167
|
|
|
135
168
|
[Apache-2.0](LICENSE).
|
package/assets/memory/AGENTS.md
CHANGED
|
@@ -25,6 +25,28 @@
|
|
|
25
25
|
- End files with exactly one trailing newline and no trailing whitespace.
|
|
26
26
|
- When editing existing code, match its established style instead of imposing a different one.
|
|
27
27
|
|
|
28
|
+
### Task Execution (Always-On)
|
|
29
|
+
|
|
30
|
+
- For long or complex tasks - or any task you judge to warrant it - break the work into smaller, well-scoped subtasks and complete them incrementally, validating each subtask before moving to the next.
|
|
31
|
+
- Map the dependencies between subtasks before starting, and do only the decomposition the task genuinely needs - never over-decompose simple work.
|
|
32
|
+
|
|
33
|
+
<!-- enigma:parallel-subagents:start -->
|
|
34
|
+
- When subtasks are genuinely independent and your runtime can spawn sub-agents (parallel task or sub-agent tools), delegate them to sub-agents that run in parallel to finish faster, then reconcile their results into a coherent whole. If the runtime has no sub-agent support, execute the subtasks sequentially.
|
|
35
|
+
- Only parallelize independent work; never spawn sub-agents for trivial, tightly-coupled, or strictly sequential tasks. Keep each sub-agent's responsibility well-scoped and validate what it returns.
|
|
36
|
+
<!-- enigma:parallel-subagents:end -->
|
|
37
|
+
|
|
38
|
+
<!-- enigma:output-style:start -->
|
|
39
|
+
### Output Style (Token-Efficient)
|
|
40
|
+
|
|
41
|
+
- Default to **{{output-level}}** compression in conversational prose: cut filler, pleasantries, and hedging while keeping every technical fact, exact identifier, and code block intact. Brevity must never drop substance or change a technical claim.
|
|
42
|
+
- Levels (the user can switch any time by asking - e.g. "be more terse", "full", "ultra", or "normal mode" to turn it off):
|
|
43
|
+
- **lite** - professional and tight: drop filler and hedging, keep correct grammar and the user's language. The safe default.
|
|
44
|
+
- **full** - drop articles and use fragments where meaning stays unambiguous; prefer short synonyms ("fix", not "implement a solution for").
|
|
45
|
+
- **ultra** - telegraphic: one word where one word suffices, arrows for causality (X -> Y). Never abbreviate code symbols, function/API names, paths, or error strings.
|
|
46
|
+
- Auto-clarity: revert to full prose for security warnings, irreversible or destructive action confirmations, and any multi-step sequence where compression would make the order or meaning ambiguous. Resume after the critical part.
|
|
47
|
+
- Boundaries: code, comments, commit messages, and PR text are always written normally - compression applies only to chat prose. Always respond in the user's language regardless of level.
|
|
48
|
+
<!-- enigma:output-style:end -->
|
|
49
|
+
|
|
28
50
|
---
|
|
29
51
|
|
|
30
52
|
## Core Identity
|
package/assets/memory/CLAUDE.md
CHANGED
|
@@ -25,6 +25,28 @@
|
|
|
25
25
|
- End files with exactly one trailing newline and no trailing whitespace.
|
|
26
26
|
- When editing existing code, match its established style instead of imposing a different one.
|
|
27
27
|
|
|
28
|
+
### Task Execution (Always-On)
|
|
29
|
+
|
|
30
|
+
- For long or complex tasks - or any task you judge to warrant it - break the work into smaller, well-scoped subtasks and complete them incrementally, validating each subtask before moving to the next.
|
|
31
|
+
- Map the dependencies between subtasks before starting, and do only the decomposition the task genuinely needs - never over-decompose simple work.
|
|
32
|
+
|
|
33
|
+
<!-- enigma:parallel-subagents:start -->
|
|
34
|
+
- When subtasks are genuinely independent and your runtime can spawn sub-agents (parallel task or sub-agent tools), delegate them to sub-agents that run in parallel to finish faster, then reconcile their results into a coherent whole. If the runtime has no sub-agent support, execute the subtasks sequentially.
|
|
35
|
+
- Only parallelize independent work; never spawn sub-agents for trivial, tightly-coupled, or strictly sequential tasks. Keep each sub-agent's responsibility well-scoped and validate what it returns.
|
|
36
|
+
<!-- enigma:parallel-subagents:end -->
|
|
37
|
+
|
|
38
|
+
<!-- enigma:output-style:start -->
|
|
39
|
+
### Output Style (Token-Efficient)
|
|
40
|
+
|
|
41
|
+
- Default to **{{output-level}}** compression in conversational prose: cut filler, pleasantries, and hedging while keeping every technical fact, exact identifier, and code block intact. Brevity must never drop substance or change a technical claim.
|
|
42
|
+
- Levels (the user can switch any time by asking - e.g. "be more terse", "full", "ultra", or "normal mode" to turn it off):
|
|
43
|
+
- **lite** - professional and tight: drop filler and hedging, keep correct grammar and the user's language. The safe default.
|
|
44
|
+
- **full** - drop articles and use fragments where meaning stays unambiguous; prefer short synonyms ("fix", not "implement a solution for").
|
|
45
|
+
- **ultra** - telegraphic: one word where one word suffices, arrows for causality (X -> Y). Never abbreviate code symbols, function/API names, paths, or error strings.
|
|
46
|
+
- Auto-clarity: revert to full prose for security warnings, irreversible or destructive action confirmations, and any multi-step sequence where compression would make the order or meaning ambiguous. Resume after the critical part.
|
|
47
|
+
- Boundaries: code, comments, commit messages, and PR text are always written normally - compression applies only to chat prose. Always respond in the user's language regardless of level.
|
|
48
|
+
<!-- enigma:output-style:end -->
|
|
49
|
+
|
|
28
50
|
---
|
|
29
51
|
|
|
30
52
|
## Core Identity
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.0.0",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Backend/API architecture: controller-service-repository layering, API and request optimization, server-side caching (Redis), and Zod boundary validation.",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "c442bc9e39a7710cb709ef2abb8d15ecd8aa16ed4f5c8af92b7af6877401cba4"
|
|
8
8
|
}
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.1.1",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Ciphera code style conventions (formatting, naming, imports, comments, code-level anti-patterns; TypeScript-first, language-agnostic).",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "74f638aec13e8c93257fe1ad604c28b07e9a7c456796a4ceefcc99217d9e7039"
|
|
8
8
|
}
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.0.0",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Pre-delivery self-review gate, prioritized review dimensions, and change-quality criteria.",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "3d3bbe0602d5bbb4afe37648fe3c2fa39376b1bcbac5d8c441f01fad1e866ed0"
|
|
8
8
|
}
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.4.0",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Core engineering execution policy and harness orchestration (highest-authority rules).",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "c9c69c59516794311cb7b306ed4d4ad971824de3689a39c2b86c7669c73f2e8b"
|
|
8
8
|
}
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.0.0",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Senior database architecture policy: query optimization, anti-duplication/normalization, scalability, and RGPD/GDPR encryption.",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "c4617ee8d1a57d9621c81bef3093e94de91f79eec0cc0ead41f6d18dd443e623"
|
|
8
8
|
}
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.0.0",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Reproduce-isolate-fix debugging methodology with root-cause discipline and regression verification.",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "14b0064c8b33a0dc85e51464b05005cf5801c756b1101789a6924b9548420f6b"
|
|
8
8
|
}
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.0.0",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Dependency and supply-chain security: lockfiles and reproducible installs, version pinning, vulnerability auditing, vetting/minimizing packages, vendoring, and SBOM/provenance.",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "6375d835c2aef2c9bd31ce116444dc3d796f510f9970a213aa3ac4696d7e21b9"
|
|
8
8
|
}
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.1.0",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Frontend architecture: reusable components, abstraction thresholds, state management, and optimistic UI with rollback.",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "33fa1e9f667ef26203a3d6c892121efe12b0cddb706c195492fa97e080fba115"
|
|
8
8
|
}
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.0.0",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Application and AI-agent security: secrets, authn/authz (least privilege), OWASP Top 10, transport/crypto baseline, secure logging, and agent/MCP/tool-use safety.",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "9971e9d9127397d0152e89d24aad3191e2935e55a8483db7fd15f5d4d7a60e7a"
|
|
8
8
|
}
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.0.0",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Test strategy, coverage gates, deterministic tests, mocking discipline, and regression-first bug fixing.",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "d19fa8ec7985ed231478be504d3c80360897f555d0bc0624bea19c091f459fb0"
|
|
8
8
|
}
|
|
@@ -3,6 +3,6 @@
|
|
|
3
3
|
"version": "1.0.0",
|
|
4
4
|
"provider": "FJRG2007/enigma",
|
|
5
5
|
"description": "Strict frontend + backend schema validation, schema consistency, and safe client-facing error handling.",
|
|
6
|
-
"cliVersion": "1.6.
|
|
6
|
+
"cliVersion": "1.6.4",
|
|
7
7
|
"sha": "a33622a2f810ee4cea39824cb1a7ca34b355a917d4224025df50d77dd74f0b3a"
|
|
8
8
|
}
|
package/bin/checksums.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
|
-
"enigma-darwin-arm64": "
|
|
3
|
-
"enigma-linux-arm64": "
|
|
4
|
-
"enigma-linux-x64": "
|
|
5
|
-
"enigma-win32-x64.exe": "
|
|
2
|
+
"enigma-darwin-arm64": "0250f3304140999cf52c768e658e631e3b791df6c254c94e9aab0df5b41750d2",
|
|
3
|
+
"enigma-linux-arm64": "c652278b26ab717e8d1a9d2729b342cebd4b07b99716bb0e22f60a832271ae8e",
|
|
4
|
+
"enigma-linux-x64": "b5dc8ffd1f9e870b99936b114eca90a5192a7933acca93a2df524f9ba2df25dd",
|
|
5
|
+
"enigma-win32-x64.exe": "f7e16827e385d48fb1298c1eee1fe4e5f3f212b2d7eb0cbffab1c631eeb76725"
|
|
6
6
|
}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "enigma-cli",
|
|
3
|
-
"version": "1.6.
|
|
3
|
+
"version": "1.6.4",
|
|
4
4
|
"description": "Everything you need to work with a coding agent: install shared policy skills for Claude Code, OpenAI Codex and opencode, and set up portable git security hooks.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|