gabbe-kit 1.1.1 → 1.1.3
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/LICENSE +1 -1
- package/README.md +65 -17
- package/agents/AGENTS.md +1 -1
- package/agents/CONSTITUTION.md +1 -1
- package/agents/guides/ai/ai-agentic.md +3 -1
- package/agents/guides/ops/cost-optimization.md +1 -1
- package/agents/guides/ops/troubleshooting-guide.md +2 -2
- package/agents/scripts/verify_e2e_init_flows.py +1 -1
- package/agents/skills/00-index.md +2 -2
- package/agents/skills/architecture/visual-whiteboarding.skill.md +17 -0
- package/agents/skills/coding/performant-php.skill.md +17 -0
- package/agents/templates/coordination/AGENTS_TEMPLATE.md +1 -1
- package/agents/templates/core/MCP_CONFIG_TEMPLATE.json +33 -2
- package/agents/templates/product/PRD_TEMPLATE.md +1 -1
- package/bin/install.js +24 -1
- package/docs/ARCHITECTURE.md +165 -0
- package/docs/CLI_REFERENCE.md +10 -7
- package/docs/FEATURES_AND_INNOVATIONS.md +208 -0
- package/docs/INSTALL.md +4 -1
- package/docs/MCP_CONFIGURATIONS.md +56 -4
- package/docs/PLATFORM_CONTROLS.md +1 -1
- package/docs/POST_INSTALL.md +5 -4
- package/docs/QUICK_COMMANDS.md +3 -3
- package/docs/QUICK_GUIDE.md +22 -21
- package/docs/README_FULL.md +62 -54
- package/docs/ROADMAP.md +100 -0
- package/docs/V1_RELEASE_CHECKLIST.md +5 -3
- package/docs/VERIFICATION_GUIDE.md +8 -7
- package/docs/assets/GABBE.png +0 -0
- package/docs/reports/duplication-report.md +6 -6
- package/package.json +3 -2
- package/scripts/init.py +13 -25
package/docs/QUICK_GUIDE.md
CHANGED
|
@@ -32,8 +32,8 @@ AI coding agents suffer from three compounding problems:
|
|
|
32
32
|
## 5-Minute Setup Checklist
|
|
33
33
|
|
|
34
34
|
```bash
|
|
35
|
-
# 1. Download & Run the Installer
|
|
36
|
-
curl -
|
|
35
|
+
# 1. Download & Run the Installer (uses npx gabbe-kit init when Node is present)
|
|
36
|
+
curl -fsSL https://raw.githubusercontent.com/andreibesleaga/GABBE/main/install.sh | sh
|
|
37
37
|
|
|
38
38
|
# OR if you have the repo cloned:
|
|
39
39
|
python3 GABBE/scripts/init.py
|
|
@@ -62,7 +62,7 @@ python3 GABBE/scripts/init.py
|
|
|
62
62
|
- Open `agents/AGENTS.md`: Check `Tech Stack` section.
|
|
63
63
|
- Verify `test_cmd` and `lint_cmd` match your project.
|
|
64
64
|
- Open `agents/CONSTITUTION.md`: Review project laws.
|
|
65
|
-
- Adjust Article I (
|
|
65
|
+
- Adjust Article I (Test-First Mandate) if needed.
|
|
66
66
|
|
|
67
67
|
## 6. Git Tracking (Important)
|
|
68
68
|
- To keep the initial structure of `agents/memory/` and `project/` in your repository but prevent Git from tracking the continuous autonomous modifications your agents will make to them locally, run:
|
|
@@ -74,10 +74,10 @@ python3 GABBE/scripts/init.py
|
|
|
74
74
|
|
|
75
75
|
## 🚀 GABBE CLI (Experimental)
|
|
76
76
|
|
|
77
|
-
GABBE contains a **
|
|
77
|
+
GABBE contains a **lightweight CLI** (`gabbe`; three runtime dependencies: `requests`, `PyYAML`, `jsonschema`) which powers the "Hybrid Mode". It bridges the gap between flexible Markdown files and a robust SQLite database. It's an experimental work-in-progress and you can do without the whole package only with the rest of the kit.
|
|
78
78
|
|
|
79
79
|
### Prerequisites
|
|
80
|
-
- Python 3.
|
|
80
|
+
- Python 3.9+
|
|
81
81
|
- **LLM API Key**: For Brain/Route features, set `GABBE_API_KEY` (OpenAI-compatible).
|
|
82
82
|
|
|
83
83
|
**Environment Variables** (full reference in [CLI_REFERENCE.md](CLI_REFERENCE.md#environment-variables)):
|
|
@@ -129,10 +129,10 @@ python scripts/fill_placeholders.py
|
|
|
129
129
|
| `gabbe verify --chaos` | **Resilience**: fault-injection self-checks (fail-closed tool, hard-stop, escalation). |
|
|
130
130
|
| `gabbe eval` | **Skill evals**: deterministic self-check; `--live` scores via the model. |
|
|
131
131
|
| `gabbe doctor` | **Autodetect**: OS/runtimes/agents + post-install MCP next-steps. |
|
|
132
|
-
| `gabbe update` / `gabbe uninstall` | Additive refresh / manifest-backed removal (for `gabbe`-CLI-managed kits; npx/curl
|
|
132
|
+
| `gabbe update` / `gabbe uninstall` | Additive refresh / manifest-backed removal (for `gabbe`-CLI-managed kits and wizard installs; npx/curl installs aren't manifest-tracked). |
|
|
133
133
|
| `gabbe status`| **Dashboard**: Visualizes project phase and task progress. |
|
|
134
134
|
| `gabbe brain` | **Meta-Cognition**: Activates Active Inference loop or Evolutionary Prompt Optimization (Requires API Key). |
|
|
135
|
-
| `gabbe route` | **Cost Router**: Arbitrates between Local and Remote LLMs based on task complexity (
|
|
135
|
+
| `gabbe route` | **Cost Router**: Arbitrates between Local and Remote LLMs based on task complexity (prompts of 100+ characters or with code blocks are rated by the LLM and need `GABBE_API_KEY`; without a key a fallback heuristic is used). |
|
|
136
136
|
| `gabbe forecast`| **Strategic Forecast**: Projects remaining work cost and tokens based on historical run data. |
|
|
137
137
|
| `gabbe serve-mcp` | **MCP Gateway**: Zero-dependency JSON-RPC Model Context Protocol server for standalone agents to access tools safely. |
|
|
138
138
|
| `gabbe runs` | **Run History**: List recent agent runs with status, cost, and timestamps. |
|
|
@@ -297,7 +297,7 @@ Uses Active Inference to plan, route between local/remote models, and learn from
|
|
|
297
297
|
### Activate Loki Mode (Large Projects)
|
|
298
298
|
|
|
299
299
|
**Using the CLI:**
|
|
300
|
-
> `gabbe brain activate`
|
|
300
|
+
> `gabbe brain activate` prints the model's recommended next action; it does not start Loki.
|
|
301
301
|
Or activate the swarm skill explicitly:
|
|
302
302
|
> Activate `agents/skills/brain/loki-mode.skill.md` with your goal.
|
|
303
303
|
|
|
@@ -316,20 +316,20 @@ Multi-agent swarm with 30+ specialized personas for projects >5 features or >20
|
|
|
316
316
|
```
|
|
317
317
|
GABBE/
|
|
318
318
|
scripts/init.py <- Installer Wizard (Run this first)
|
|
319
|
-
README_FULL.md
|
|
320
|
-
QUICK_GUIDE.md
|
|
319
|
+
docs/README_FULL.md <- Complete step-by-step guide
|
|
320
|
+
docs/QUICK_GUIDE.md <- This file
|
|
321
321
|
agents/ <- The actual kit payload
|
|
322
322
|
AGENTS.md <- Universal config template
|
|
323
323
|
CONSTITUTION.md <- Immutable project law
|
|
324
324
|
scripts/setup-context.sh <- Internal wiring script (wrapped by scripts/init.py)
|
|
325
325
|
skills/ <- 214 agent capability packages (💯)
|
|
326
|
-
|
|
326
|
+
coding/ <- (tdd, refactor, debug, git...)
|
|
327
327
|
security/ <- (audit, threat-model...)
|
|
328
|
-
|
|
328
|
+
architecture/ <- (design, review, patterns...)
|
|
329
329
|
templates/ <- 100 fill-in-the-blank documents
|
|
330
330
|
guides/ <- 86 domain & process guides
|
|
331
|
-
|
|
332
|
-
|
|
331
|
+
personas/ <- 36 specialized roles (Loki Mode)
|
|
332
|
+
memory/ <- project state, continuity, audit log
|
|
333
333
|
```
|
|
334
334
|
|
|
335
335
|
---
|
|
@@ -399,7 +399,7 @@ The script detects your selected agents and generates the correct format for eac
|
|
|
399
399
|
|---|---|---|
|
|
400
400
|
| **Cursor** | `.mdc` rules | `.cursor/rules/*.mdc` |
|
|
401
401
|
| **VS Code / Copilot** | Folders + Config | `.github/skills/<slug>/` |
|
|
402
|
-
| **Claude Code** |
|
|
402
|
+
| **Claude Code** | `SKILL.md` folders | `.claude/skills/<slug>/SKILL.md` (one per skill) |
|
|
403
403
|
| **Gemini / Antigravity** | Settings | `.gemini/settings.json` points to `agents/skills` |
|
|
404
404
|
|
|
405
405
|
This means you write a skill once in `agents/skills/` and it runs everywhere.
|
|
@@ -657,7 +657,7 @@ Goal: Mandate SDD for all new features
|
|
|
657
657
|
Rule: No code without an approved PRD.md
|
|
658
658
|
Actions:
|
|
659
659
|
- Make spec-writer.skill the entry point for all feature requests
|
|
660
|
-
- Enforce
|
|
660
|
+
- Enforce 10-gate quality system in CI/CD
|
|
661
661
|
- Track and repay tech debt with tech-debt.skill
|
|
662
662
|
- Measure: specification-to-code ratio, coverage, architectural violations
|
|
663
663
|
```
|
|
@@ -678,14 +678,15 @@ Actions:
|
|
|
678
678
|
|
|
679
679
|
| Server | Install | Why |
|
|
680
680
|
|---|---|---|
|
|
681
|
-
| **Context-7** | `npx @context7
|
|
681
|
+
| **Context-7** | `npx @upstash/context7-mcp` | Up-to-date SDK docs (prevents API hallucination) |
|
|
682
682
|
| **Sequential Thinking** | `npx @modelcontextprotocol/server-sequential-thinking` | Chain-of-thought before acting |
|
|
683
683
|
| **GitHub MCP** | `npx @modelcontextprotocol/server-github` | PR review, issues, code search |
|
|
684
|
+
| **GitHits** | `npx githits@latest init` | Navigate open-source dependency source/docs (no clone, no key) |
|
|
684
685
|
| **PostgreSQL MCP** | `npx @modelcontextprotocol/server-postgres` | Live schema introspection |
|
|
685
686
|
| **Semgrep MCP** | `pip install semgrep-mcp` | In-agent SAST security scanning |
|
|
686
687
|
| **Brave Search MCP** | `npx @modelcontextprotocol/server-brave-search` | Authoritative web research |
|
|
687
688
|
| **Playwright MCP** | `npx @playwright/mcp` | Browser automation for visual TDD |
|
|
688
|
-
| **Sentry MCP** | `npx @sentry/mcp` | Error tracking and bug context |
|
|
689
|
+
| **Sentry MCP** | `npx @sentry/mcp-server` | Error tracking and bug context |
|
|
689
690
|
| **Qdrant MCP** | `docker run qdrant/qdrant` + MCP server | Long-term semantic memory |
|
|
690
691
|
|
|
691
692
|
See `templates/core/MCP_CONFIG_TEMPLATE.json` for the full catalog with security configuration.
|
|
@@ -745,7 +746,7 @@ If the self-healing loop frequently fails or a specific skill repeatedly produce
|
|
|
745
746
|
```
|
|
746
747
|
|
|
747
748
|
**Using Pure Agent Mode (No CLI):**
|
|
748
|
-
> "We continually fail when writing React hooks. Invoke the `meta-optimize` skill. Read the last 5 chat messages, identify why your previous attempts failed, and directly edit `agents/skills/coding/
|
|
749
|
+
> "We continually fail when writing React hooks. Invoke the `meta-optimize` skill. Read the last 5 chat messages, identify why your previous attempts failed, and directly edit `agents/skills/coding/ui-gen.skill.md` to add new constraints preventing this failure in the future. Log the change to `meta-evolution.log`."
|
|
749
750
|
|
|
750
751
|
### Human-in-the-Loop — When to Pause and Ask
|
|
751
752
|
```
|
|
@@ -837,7 +838,7 @@ No human needed for:
|
|
|
837
838
|
|
|
838
839
|
| Category | Templates |
|
|
839
840
|
|---|---|
|
|
840
|
-
| **Core** | `AGENTS`, `MCP_CONFIG`, `DEVCONTAINER`, `DEV_SPACE`, `PLAN`, `TASKS`, `AUDIT_LOG`, `SDLC_TRACKER`, `SESSION_SNAPSHOT`, `SWARM_CONFIG`, `AGENT_HANDSHAKE`, `SYSTEM_ANALYSIS
|
|
841
|
+
| **Core** | `AGENTS`, `MCP_CONFIG`, `DEVCONTAINER`, `DEV_SPACE`, `PLAN`, `TASKS`, `AUDIT_LOG`, `SDLC_TRACKER`, `SESSION_SNAPSHOT`, `SWARM_CONFIG`, `AGENT_HANDSHAKE`, `SYSTEM_ANALYSIS` (project state, continuity and the voting log live in `agents/memory/`: `PROJECT_STATE.md`, `CONTINUITY.md`, `episodic/VOTING_LOG.md` (created at run time)) |
|
|
841
842
|
| **Arch** | `ADR`, `ARCH_DECISION_FRAMEWORK`, `ARCHITECTURE_DECISION_MATRIX`, `ARCHITECTURE_REVIEW`, `ARCHITECTURE_VIEWS`, `C4_ARCHITECTURE`, `CONTEXT_MAP`, `DOMAIN_MODEL`, `SYSTEM_CONTEXT`, `SWARM_ARCHITECTURE`, `DESIGN_PATTERN_USAGE`, `CAPABILITY_MAP`, `LEGACY_AUDIT` |
|
|
842
843
|
| **Reqs** | `PRD`, `SPEC`, `BUSINESS_CASE`, `CAPABILITY_MAP`, `EMPATHY_MAP`, `NFR`, `QUALITY_ATTRIBUTES`, `REQUIREMENTS_REVIEW`, `STAKEHOLDER_REGISTER`, `TRACEABILITY_MATRIX`, `ETHICAL_IMPACT_ASSESSMENT` |
|
|
843
844
|
| **Eng** | `CLEAN_CODE_CHECKLIST`, `SECURITY_CHECKLIST`, `THREAT_MODEL`, `TECH_DEBT`, `TEST_PLAN`, `TEST_CASE`, `INTEGRATION_SPEC`, `DATA_PIPELINE`, `DATABASE_SCHEMA`, `DESIGN_TOKENS`, `E2E_TEST_SUITE`, `SAFETY_POLICY` |
|
|
@@ -896,7 +897,7 @@ python3 GABBE/scripts/init.py
|
|
|
896
897
|
*See README.md for quick reference.*
|
|
897
898
|
*See README_FULL.md for full workflow guides with Mermaid diagrams.*
|
|
898
899
|
*See skills/00-index.md for complete skills registry with installation instructions.*
|
|
899
|
-
*See agents/skills/brain/
|
|
900
|
+
*See agents/skills/brain/loki-mode.skill.md for Loki Mode multi-agent orchestration.*
|
|
900
901
|
*See agents/skills/brain/README.md for complete brain documentation.*
|
|
901
902
|
|
|
902
903
|
## 🛡️ Security & Guardrails
|
package/docs/README_FULL.md
CHANGED
|
@@ -19,7 +19,7 @@ It contains:
|
|
|
19
19
|
- **100 Templates** (standardized documents)
|
|
20
20
|
- **86 Guides** (language & domain expertise)
|
|
21
21
|
- **36 Personas** (specialized roles)
|
|
22
|
-
- **
|
|
22
|
+
- **66 MCP servers** (configuration and guides for AI tools)
|
|
23
23
|
- **Brain Mode** (meta-cognitive orchestration)
|
|
24
24
|
- **Loki Mode** (multi-agent swarm engineering personas team for large projects)
|
|
25
25
|
|
|
@@ -34,26 +34,28 @@ It contains:
|
|
|
34
34
|
3. [Quick Start (5 min)](#3-quick-start-5-min)
|
|
35
35
|
4. [Kit Structure Map](#4-kit-structure-map)
|
|
36
36
|
5. [Workflow 1: New Project from Scratch](#5-workflow-1-new-project-from-scratch)
|
|
37
|
-
6. [Workflow 2: Refactoring & Bugfixing Existing Project](#6-workflow-2-refactoring
|
|
38
|
-
7. [Self-Healing + Research Loop](#7-self-healing
|
|
37
|
+
6. [Workflow 2: Refactoring & Bugfixing Existing Project](#6-workflow-2-refactoring--bugfixing-existing-project)
|
|
38
|
+
7. [Self-Healing + Research Loop](#7-self-healing--research-loop)
|
|
39
|
+
8. [Cognitive Architecture Integration (Evolution & Healing)](#8-cognitive-architecture-integration-evolution--healing)
|
|
39
40
|
9. [Multi-Agent Systems (MAS)](#9-multi-agent-systems-mas)
|
|
40
|
-
10. [Architecture & Design Patterns](#10-architecture
|
|
41
|
+
10. [Architecture & Design Patterns](#10-architecture--design-patterns)
|
|
41
42
|
11. [Agentic Patterns (Advanced AI)](#11-agentic-patterns-advanced-ai)
|
|
42
43
|
12. [Testing Strategy](#12-testing-strategy)
|
|
43
44
|
13. [Enterprise Domains (Infra, Data, Integration)](#13-enterprise-domains-infra-data-integration)
|
|
44
|
-
14. [Environment & Deployment (Local/Remote/Cloud)](#14-environment
|
|
45
|
+
14. [Environment & Deployment (Local/Remote/Cloud)](#14-environment--deployment-localremotecloud)
|
|
45
46
|
15. [Legacy Systems (COBOL, Mainframe)](#15-legacy-systems-cobol-mainframe)
|
|
46
|
-
16. [Future Tech & Adaptive Skills (2026-2030)](#16-future-tech
|
|
47
|
-
17. [System Quality & Evolution (SRE, Performance)](#17-system-quality
|
|
48
|
-
18. [System Lifecycle & Traceability](#18-system-lifecycle
|
|
47
|
+
16. [Future Tech & Adaptive Skills (2026-2030)](#16-future-tech--adaptive-skills-2026-2030)
|
|
48
|
+
17. [System Quality & Evolution (SRE, Performance)](#17-system-quality--evolution-sre-performance)
|
|
49
|
+
18. [System Lifecycle & Traceability](#18-system-lifecycle--traceability)
|
|
49
50
|
19. [Skills Reference](#19-skills-reference)
|
|
50
51
|
20. [Templates Reference](#20-templates-reference)
|
|
51
52
|
21. [MCP Configuration](#21-mcp-configuration)
|
|
52
53
|
22. [Extending the Kit](#22-extending-the-kit)
|
|
53
54
|
23. [Loki Mode (Large Projects)](#23-loki-mode-large-projects)
|
|
54
|
-
24. [
|
|
55
|
-
25. [
|
|
56
|
-
26. [
|
|
55
|
+
24. [What's Inside?](#24-whats-inside)
|
|
56
|
+
25. [Common Actions (Copy-Paste Prompts)](#25--common-actions-copy-paste-prompts)
|
|
57
|
+
26. [Guides by Technology Stack](#26-guides-by-technology-stack)
|
|
58
|
+
27. [Troubleshooting](#27-troubleshooting)
|
|
57
59
|
|
|
58
60
|
---
|
|
59
61
|
|
|
@@ -93,14 +95,18 @@ The system features a **Brain Mode** that supersedes standard execution. It uses
|
|
|
93
95
|
|
|
94
96
|
```bash
|
|
95
97
|
# Activate Brain Mode
|
|
96
|
-
|
|
98
|
+
gabbe brain activate
|
|
97
99
|
```
|
|
98
100
|
|
|
101
|
+
Or ask your agent in chat: "Activate Brain Mode. Goal: Build a SaaS platform."
|
|
102
|
+
|
|
99
103
|
### Key Capabilities
|
|
100
104
|
- **Active Inference Loop**: Continuously compares "Expected State" vs "Actual State".
|
|
101
105
|
- **Dynamic Cost Routing**: Routes simple tasks to **Local LLMs** and complex ones to **Remote SOTA Models**.
|
|
102
106
|
- **Episodic Memory**: Learns from past failures and successes across projects.
|
|
103
107
|
|
|
108
|
+
These are the agent-mode behaviours of `brain-mode.skill`. The `gabbe brain` CLI is smaller: it reads task counts, picks a prompt gene (epsilon-greedy), makes one LLM call and rewards the gene; routing is `gabbe route`, and it does no episodic recall (see [ADR-0002](adr/0002-brain-active-inference-runtime.md)).
|
|
109
|
+
|
|
104
110
|
Read more in [AGENTS.md](../agents/AGENTS.md).
|
|
105
111
|
|
|
106
112
|
---
|
|
@@ -131,11 +137,11 @@ python3 scripts/init.py
|
|
|
131
137
|
|
|
132
138
|
## 3.1. GABBE CLI (experimental)
|
|
133
139
|
|
|
134
|
-
GABBE has a **
|
|
140
|
+
GABBE has a **lightweight CLI** (`gabbe`; three runtime dependencies: `requests`, `PyYAML`, `jsonschema`) which powers the "Hybrid Mode". It bridges the gap between flexible Markdown files and a robust SQLite database.
|
|
135
141
|
It's an experimental work-in-progress and you can do without the whole package only with the rest of the kit.
|
|
136
142
|
|
|
137
143
|
### Prerequisites
|
|
138
|
-
- Python 3.
|
|
144
|
+
- Python 3.9+
|
|
139
145
|
- **LLM API Key**: For Brain/Route features, set `GABBE_API_KEY` (OpenAI-compatible).
|
|
140
146
|
|
|
141
147
|
**Environment Variables** (full reference in [CLI_REFERENCE.md](CLI_REFERENCE.md#environment-variables)):
|
|
@@ -160,7 +166,7 @@ It's an experimental work-in-progress and you can do without the whole package o
|
|
|
160
166
|
| `GABBE_POLICY_FILE` | `project/policies.yml` | Path to YAML policy file for tool access control |
|
|
161
167
|
| `GABBE_ESCALATION_MODE` | `cli` | Escalation mode: `cli` (interactive), `file` (pause), `silent` (auto-reject) |
|
|
162
168
|
| `GABBE_SUBPROCESS_TIMEOUT` | `300` | Timeout for verify shell commands (seconds) |
|
|
163
|
-
| `GABBE_MCP_TOKEN` | *(unset)* |
|
|
169
|
+
| `GABBE_MCP_TOKEN` | *(unset)* | MCP clients must provide this token to authenticate. While it is unset (and `GABBE_MCP_INSECURE` is off) the server refuses tool calls |
|
|
164
170
|
| `GABBE_MCP_ALLOWED_COMMANDS` | *(unset)* | Comma-separated list of executables permitted via MCP `run_command` |
|
|
165
171
|
| `GABBE_OTEL_ENABLED` | `false` | Enable OpenTelemetry tracing |
|
|
166
172
|
|
|
@@ -187,7 +193,7 @@ gabbe --help
|
|
|
187
193
|
| `gabbe update` / `gabbe uninstall` | **Reversible install**: additive refresh / manifest-backed removal (`--dry-run`, `--purge`, `--global`, `--dir`). |
|
|
188
194
|
| `gabbe status`| **Dashboard**: Visualizes project phase and task progress. |
|
|
189
195
|
| `gabbe brain` | **Meta-Cognition**: Activates Active Inference loop or Evolutionary Prompt Optimization (Requires API Key). |
|
|
190
|
-
| `gabbe route` | **Cost Router**: Arbitrates between Local and Remote LLMs based on task complexity (
|
|
196
|
+
| `gabbe route` | **Cost Router**: Arbitrates between Local and Remote LLMs based on task complexity (prompts of 100+ characters or with code blocks are rated by the LLM and need `GABBE_API_KEY`; without a key a fallback heuristic is used). |
|
|
191
197
|
| `gabbe forecast`| **Strategic Forecast**: Projects remaining work cost and tokens based on historical run data. |
|
|
192
198
|
| `gabbe serve-mcp` | **MCP Gateway**: Zero-dependency JSON-RPC Model Context Protocol server for standalone agents to access tools safely. |
|
|
193
199
|
| `gabbe runs [--status STATUS] [--limit N]` | **Run History**: List recent agent runs with status, cost, and timestamps. |
|
|
@@ -202,7 +208,7 @@ gabbe --help
|
|
|
202
208
|
The experimental `gabbe` CLI supports a **platform control layer**. It covers budget enforcement, cost and token controls, hard stops, policy rules, the tool gateway, audit tracing, human escalation, and deterministic replay. Detailed documentation is available in [`PLATFORM_CONTROLS.md`](PLATFORM_CONTROLS.md).
|
|
203
209
|
|
|
204
210
|
### Architecture
|
|
205
|
-
GABBE
|
|
211
|
+
GABBE uses a **Hybrid Architecture** where agents and humans interact via Markdown, but the system of record is SQLite.
|
|
206
212
|
|
|
207
213
|
```mermaid
|
|
208
214
|
graph TD
|
|
@@ -352,7 +358,7 @@ Uses Active Inference to plan, route between local/remote models, and learn from
|
|
|
352
358
|
### Activate Loki Mode (Large Projects)
|
|
353
359
|
|
|
354
360
|
**Using the CLI:**
|
|
355
|
-
> `gabbe brain activate`
|
|
361
|
+
> `gabbe brain activate` prints the model's recommended next action; it does not start Loki. Start Loki with the skill below.
|
|
356
362
|
Or activate the swarm skill explicitly:
|
|
357
363
|
> Activate `agents/skills/brain/loki-mode.skill.md` with your goal.
|
|
358
364
|
|
|
@@ -406,7 +412,7 @@ graph TB
|
|
|
406
412
|
L --> M1
|
|
407
413
|
end
|
|
408
414
|
subgraph "Templates Layer"
|
|
409
|
-
T[templates/<br/>
|
|
415
|
+
T[templates/<br/>100 fill-in-the-blank docs]
|
|
410
416
|
end
|
|
411
417
|
```
|
|
412
418
|
|
|
@@ -552,7 +558,7 @@ flowchart TD
|
|
|
552
558
|
B1 -->|Yes — resuming| C[Load all memory + project state]
|
|
553
559
|
B1 -->|No — first time| D[Initialize kit]
|
|
554
560
|
|
|
555
|
-
D --> D1[setup-context.sh]
|
|
561
|
+
D --> D1[agents/scripts/setup-context.sh]
|
|
556
562
|
D1 --> D2[Adapt AGENTS.md]
|
|
557
563
|
D2 --> D3[Run audit skills]
|
|
558
564
|
|
|
@@ -612,7 +618,7 @@ flowchart TD
|
|
|
612
618
|
cp -r ~/agents/ ./
|
|
613
619
|
|
|
614
620
|
# 2. Wire up context
|
|
615
|
-
agents/setup-context.sh
|
|
621
|
+
agents/scripts/setup-context.sh
|
|
616
622
|
|
|
617
623
|
# 3. Adapt AGENTS.md
|
|
618
624
|
# - Set tech stack, test commands, lint commands
|
|
@@ -682,7 +688,7 @@ GABBE's true power lies in its **Meta-Cognitive triad**: Active Inference (`acti
|
|
|
682
688
|
|
|
683
689
|
### 8.1. Sensory MCPs to Working Memory
|
|
684
690
|
When an agent uses a sensory tool (like `visual-specs` or `excalidraw`), the parsed visual context is directly committed to the `WORKING_MEMORY.md`.
|
|
685
|
-
|
|
691
|
+
The `gabbe` CLI does not read `WORKING_MEMORY.md`; routing by `gabbe route` uses the prompt text only.
|
|
686
692
|
|
|
687
693
|
### 8.2. Enforcing Brain Mode (`activate`)
|
|
688
694
|
Brain Mode should be integrated into your development loop after significant milestones:
|
|
@@ -709,13 +715,13 @@ gabbe brain evolve --skill code-review
|
|
|
709
715
|
```
|
|
710
716
|
|
|
711
717
|
**Using Pure Agent Mode (No CLI):**
|
|
712
|
-
> "We continually fail when writing React hooks. Invoke the `meta-optimize` skill. Read the last 5 chat messages, identify why your previous attempts failed, and directly edit `agents/skills/coding/
|
|
718
|
+
> "We continually fail when writing React hooks. Invoke the `meta-optimize` skill. Read the last 5 chat messages, identify why your previous attempts failed, and directly edit `agents/skills/coding/ui-gen.skill.md` to add new constraints preventing this failure in the future. Log the change to `meta-evolution.log`."
|
|
713
719
|
|
|
714
720
|
### 8.4. Self-Healing Enforcement (`heal`)
|
|
715
721
|
The healing protocol acts as an infrastructure watchdog to recover from failures.
|
|
716
722
|
|
|
717
723
|
**Using the CLI:**
|
|
718
|
-
Checks
|
|
724
|
+
Checks that the database is reachable and that `agents/AGENTS.md`, `agents/CONSTITUTION.md` and `project/TASKS.md` exist. Run this in your CI/CD pipeline.
|
|
719
725
|
```bash
|
|
720
726
|
gabbe brain heal
|
|
721
727
|
```
|
|
@@ -728,7 +734,7 @@ gabbe brain heal
|
|
|
728
734
|
This kit includes specialized tools for building orchestrator-worker swarms and complex agent topologies.
|
|
729
735
|
|
|
730
736
|
**Key Resources:**
|
|
731
|
-
- **Guide**: `guides/multi-agent-systems.md` — Full development patterns & stack integration.
|
|
737
|
+
- **Guide**: `guides/ai/multi-agent-systems.md` — Full development patterns & stack integration.
|
|
732
738
|
- **Skill**: `multi-agent-orch` — Plan and orchestrate agent swarms.
|
|
733
739
|
- **Skill**: `agent-protocol` — Define inter-agent communication schemas.
|
|
734
740
|
- **Template**: `AGENT_PROFILE_TEMPLATE.md` — Define roles and personalities.
|
|
@@ -752,7 +758,7 @@ Embeds 2025-standard patterns into your workflow.
|
|
|
752
758
|
- **Template**: `ARCH_DECISION_FRAMEWORK.md` — Matrix for Architectural decision making.
|
|
753
759
|
- **Template**: `DESIGN_PATTERN_USAGE.md` — Justify complex pattern choices.
|
|
754
760
|
- **Template**: `CLEAN_CODE_CHECKLIST.md` — Quality gate for PRs.
|
|
755
|
-
- **Guide**: `guides/design-patterns.md` — Catalog of modern patterns.
|
|
761
|
+
- **Guide**: `guides/patterns/design-patterns.md` — Catalog of modern patterns.
|
|
756
762
|
|
|
757
763
|
---
|
|
758
764
|
|
|
@@ -763,7 +769,7 @@ Tools for building self-correcting, planning, and memory-augmented agents.
|
|
|
763
769
|
**Key Resources:**
|
|
764
770
|
- **Skill**: `agentic-patterns` — Implements Reflection, ReAct, and Planning loops.
|
|
765
771
|
- **Template**: `ETHICAL_IMPACT_ASSESSMENT.md` — AI Safety & Bias check.
|
|
766
|
-
- **Guide**: `guides/agentic-patterns.md` — Deep dive into cognitive architectures.
|
|
772
|
+
- **Guide**: `guides/patterns/agentic-patterns.md` — Deep dive into cognitive architectures.
|
|
767
773
|
|
|
768
774
|
---
|
|
769
775
|
|
|
@@ -773,7 +779,7 @@ Comprehensive testing resources using Pyramid or Trophy models.
|
|
|
773
779
|
|
|
774
780
|
**Key Resources:**
|
|
775
781
|
- **Skill**: `testing-strategy` — Orchestrate Unit, Integration, E2E, and Contract testing.
|
|
776
|
-
- **Guide**: `guides/testing-strategy.md` — Complete guide to modern testing patterns.
|
|
782
|
+
- **Guide**: `guides/principles/testing-strategy.md` — Complete guide to modern testing patterns.
|
|
777
783
|
- **Template**: `TEST_PLAN_TEMPLATE.md` — Master test plan document.
|
|
778
784
|
- **Template**: `TEST_CASE_TEMPLATE.md` — Detailed test case definition.
|
|
779
785
|
- **Template**: `E2E_TEST_SUITE_TEMPLATE.md` — High-level E2E scenarios.
|
|
@@ -794,7 +800,7 @@ Specialized resources for specialized domains.
|
|
|
794
800
|
|
|
795
801
|
### Enterprise Integration
|
|
796
802
|
- **Skill**: `enterprise-integration` (ERP, CRM, Legacy patterns).
|
|
797
|
-
- **Guide**: `guides/enterprise-patterns.md` (Strangler Fig, ACL).
|
|
803
|
+
- **Guide**: `guides/patterns/enterprise-patterns.md` (Strangler Fig, ACL).
|
|
798
804
|
- **Template**: `INTEGRATION_SPEC_TEMPLATE.md`.
|
|
799
805
|
|
|
800
806
|
---
|
|
@@ -814,7 +820,7 @@ Tools for the full lifecycle: from localhost to production.
|
|
|
814
820
|
### Cloud Deployment (Outer Loop)
|
|
815
821
|
- **Skill**: `cloud-deploy` (Vercel, Railway, AWS SST).
|
|
816
822
|
- **Template**: `DEPLOY_CONFIG_TEMPLATE.md`.
|
|
817
|
-
- **Guide**: `guides/dev-environments.md`.
|
|
823
|
+
- **Guide**: `guides/ops/dev-environments.md`.
|
|
818
824
|
|
|
819
825
|
---
|
|
820
826
|
|
|
@@ -825,7 +831,7 @@ Tools for the full lifecycle: from localhost to production.
|
|
|
825
831
|
### Modernization
|
|
826
832
|
- **Skill**: `legacy-modernization` (COBOL analysis, Strangler Fig).
|
|
827
833
|
- **Template**: `LEGACY_AUDIT_TEMPLATE.md` (Risk & Knowledge audit).
|
|
828
|
-
- **Guide**: `guides/legacy-tech.md` (Mainframe DevOps, COBOL basics).
|
|
834
|
+
- **Guide**: `guides/principles/legacy-tech.md` (Mainframe DevOps, COBOL basics).
|
|
829
835
|
|
|
830
836
|
---
|
|
831
837
|
|
|
@@ -837,7 +843,7 @@ Preparing for the next wave: 6G, Agentic IoT, and Evolutionary Architecture.
|
|
|
837
843
|
- **Skill**: `emerging-tech` (6G, Matter, Vector Databases).
|
|
838
844
|
- **Skill**: `adaptive-architecture` (Local-First, WASM, CRDTs).
|
|
839
845
|
- **Template**: `ADAPTIVE_SYSTEM_TEMPLATE.md` (Evolutionary design).
|
|
840
|
-
- **Guide**: `guides/future-tech.md` (The 2030 Horizon).
|
|
846
|
+
- **Guide**: `guides/principles/future-tech.md` (The 2030 Horizon).
|
|
841
847
|
|
|
842
848
|
---
|
|
843
849
|
|
|
@@ -855,7 +861,7 @@ Resources for ensuring your software is reliable, fast, and adaptable.
|
|
|
855
861
|
- **Template**: `SAFETY_CASE.md` (Critical system assurance).
|
|
856
862
|
- **Template**: `COST_OPTIMIZATION_REPORT_TEMPLATE.md` (FinOps).
|
|
857
863
|
- **Template**: `INCIDENT_POSTMORTEM_TEMPLATE.md` (Blameless analysis).
|
|
858
|
-
- **Guide**: `guides/system-qualities.md` (The "Ilities").
|
|
864
|
+
- **Guide**: `guides/architecture/system-qualities.md` (The "Ilities").
|
|
859
865
|
|
|
860
866
|
---
|
|
861
867
|
|
|
@@ -868,7 +874,7 @@ Resources for binding Requirements to Code and Tests (The Golden Thread).
|
|
|
868
874
|
|
|
869
875
|
### Documentation
|
|
870
876
|
- **Template**: `TRACEABILITY_MATRIX_TEMPLATE.md` (Live status of requirements).
|
|
871
|
-
- **Guide**: `guides/full-system-lifecycle.md` (Definition of Done).
|
|
877
|
+
- **Guide**: `guides/processes/full-system-lifecycle.md` (Definition of Done).
|
|
872
878
|
|
|
873
879
|
---
|
|
874
880
|
|
|
@@ -1100,8 +1106,8 @@ All templates now live in categorized subdirectories under `agents/templates/`.
|
|
|
1100
1106
|
| `core/SESSION_SNAPSHOT_TEMPLATE.md` | Complete project state |
|
|
1101
1107
|
| `core/TRACEABILITY_MATRIX_TEMPLATE.md` | Traceability Matrix | Req -> Code -> Test trace |
|
|
1102
1108
|
| `core/BUG_REPORT_TEMPLATE.md` | Bug Report | Structured bug reporting |
|
|
1103
|
-
| `
|
|
1104
|
-
| `
|
|
1109
|
+
| `agents/memory/PROJECT_STATE.md` | Project State | Current SDLC phase & status |
|
|
1110
|
+
| `agents/memory/CONTINUITY.md` | Continuity Log | Past failure prevention log |
|
|
1105
1111
|
|
|
1106
1112
|
### Coordination & Brain (`templates/coordination/`, `templates/brain/`)
|
|
1107
1113
|
| Template | Purpose |
|
|
@@ -1110,7 +1116,7 @@ All templates now live in categorized subdirectories under `agents/templates/`.
|
|
|
1110
1116
|
| `coordination/SWARM_CONFIG_TEMPLATE.json` | Multi-agent configuration |
|
|
1111
1117
|
| `coordination/AGENT_PROFILE_TEMPLATE.md` | Agent Profile | Persona definition |
|
|
1112
1118
|
| `coordination/AGENT_HANDSHAKE_TEMPLATE.json` | Agent Handshake | Protocol negotiation |
|
|
1113
|
-
| `
|
|
1119
|
+
| `agents/memory/episodic/VOTING_LOG.md` (created by `swarm-consensus`; no template file) | Agent Consensus Voting Record |
|
|
1114
1120
|
| `coordination/SWARM_ARCHITECTURE_TEMPLATE.md` | Swarm Architecture | Multi-agent topology |
|
|
1115
1121
|
| `brain/ACTIVE_INFERENCE_LOOP_TEMPLATE.md` | Cognitive loop structure |
|
|
1116
1122
|
| `brain/GLOBAL_WORKSPACE_CONFIG_TEMPLATE.md` | GWT Blackboard config |
|
|
@@ -1140,7 +1146,7 @@ All templates now live in categorized subdirectories under `agents/templates/`.
|
|
|
1140
1146
|
| `architecture/SCALABILITY_ANALYSIS_TEMPLATE.md` | Architecture | Scalability bottleneck analysis |
|
|
1141
1147
|
| `architecture/SMART_CONTRACT_TEMPLATE.md` | Blockchain | Smart contract logic & security |
|
|
1142
1148
|
| `architecture/ARCHITECTURE_DECISION_MATRIX.md` | Architecture | Scoring matrix for trade-offs |
|
|
1143
|
-
| `
|
|
1149
|
+
| `brain/PROJECT_CONTEXT_TEMPLATE.md` | Core | Holistic project context for agents |
|
|
1144
1150
|
| `product/PROBLEM_STATEMENT_TEMPLATE.md` | Product | Problem definition (EARS subset) |
|
|
1145
1151
|
| `product/IDEATION_LOG_TEMPLATE.md` | Product | Brainstorming & outcome log |
|
|
1146
1152
|
|
|
@@ -1158,6 +1164,7 @@ MCP (Model Context Protocol) servers extend agent capabilities. Configure them i
|
|
|
1158
1164
|
| **Docs** | Context-7 MCP | Up-to-date SDK docs (prevents API hallucination) |
|
|
1159
1165
|
| **Reasoning** | Sequential Thinking | Chain-of-thought before acting |
|
|
1160
1166
|
| **Code Search** | GitHub MCP | PR review, code search, issue management |
|
|
1167
|
+
| **Dependencies** | GitHits MCP | Navigate open-source dependency source/docs (no clone, no key) |
|
|
1161
1168
|
| **Database** | PostgreSQL MCP | Live schema introspection |
|
|
1162
1169
|
| **Security** | Semgrep MCP | SAST scanning from within the agent |
|
|
1163
1170
|
| **Web Search** | Brave Search / Tavily | Authoritative source research |
|
|
@@ -1170,7 +1177,7 @@ MCP (Model Context Protocol) servers extend agent capabilities. Configure them i
|
|
|
1170
1177
|
| **Canvas** | tldraw MCP | Persistent visual canvas for wireframing |
|
|
1171
1178
|
| **Filesystem** | Filesystem MCP | Local file access for internal RAG |
|
|
1172
1179
|
|
|
1173
|
-
**Full coverage matrix** (
|
|
1180
|
+
**Full coverage matrix** (66 MCP servers in `MCP_CONFIG_TEMPLATE.json`):
|
|
1174
1181
|
|
|
1175
1182
|
| Integration Domain | Servers Available |
|
|
1176
1183
|
|---|---|
|
|
@@ -1182,6 +1189,7 @@ MCP (Model Context Protocol) servers extend agent capabilities. Configure them i
|
|
|
1182
1189
|
| **Observability** | Sentry, Datadog, Grafana |
|
|
1183
1190
|
| **Code Quality** | Semgrep, Snyk, SonarQube, Gitleaks, Time Complexity |
|
|
1184
1191
|
| **Project Mgmt** | GitHub, GitLab, Jira, Linear, Notion, Confluence, Slack |
|
|
1192
|
+
| **Dependencies** | GitHits (navigate open-source dependency source, docs, issues, changelogs) |
|
|
1185
1193
|
| **Cloud/Infra** | AWS Core, Kubernetes, Figma |
|
|
1186
1194
|
|
|
1187
1195
|
**Security rules:**
|
|
@@ -1218,7 +1226,7 @@ See [MCP_CONFIGURATIONS.md](MCP_CONFIGURATIONS.md) for comprehensive per-server
|
|
|
1218
1226
|
## Instructions
|
|
1219
1227
|
[Detailed steps for the agent to follow]
|
|
1220
1228
|
```
|
|
1221
|
-
3. **Register:** Run `scripts/init.py` (or `agents/setup-context.sh`) to symlink changes.
|
|
1229
|
+
3. **Register:** Run `scripts/init.py` (or `agents/scripts/setup-context.sh`) to symlink changes.
|
|
1222
1230
|
|
|
1223
1231
|
### Adding Custom MCP Servers
|
|
1224
1232
|
|
|
@@ -1319,7 +1327,7 @@ Copy and paste these exact prompts into your AI chat window to kick off standard
|
|
|
1319
1327
|
### Activate Loki Mode (Large Projects)
|
|
1320
1328
|
|
|
1321
1329
|
**Using the CLI:**
|
|
1322
|
-
> `gabbe brain activate`
|
|
1330
|
+
> `gabbe brain activate` prints the model's recommended next action; it does not start Loki. Start Loki with the skill below.
|
|
1323
1331
|
Or activate the swarm skill explicitly:
|
|
1324
1332
|
> Activate `agents/skills/brain/loki-mode.skill.md` with your goal.
|
|
1325
1333
|
|
|
@@ -1334,7 +1342,7 @@ Or activate the swarm skill explicitly:
|
|
|
1334
1342
|
|
|
1335
1343
|
| Guide | Stack | Key Topics |
|
|
1336
1344
|
|---|---|---|
|
|
1337
|
-
| `guides/
|
|
1345
|
+
| `guides/processes/full-system-lifecycle.md` | Process/SDLC | Traceability, Golden Thread, DoD |
|
|
1338
1346
|
| `guides/architecture/system-qualities.md` | Architecture/Ops | Reliability, SRE, Scalability |
|
|
1339
1347
|
| `guides/ops/production-health.md` | Ops/SRE | Health Checks & Monitoring |
|
|
1340
1348
|
| `guides/principles/future-tech.md` | Future/2030 | 6G, IoT Matter, Vector DBs, WASM |
|
|
@@ -1351,7 +1359,7 @@ Or activate the swarm skill explicitly:
|
|
|
1351
1359
|
| `guides/patterns/ai-native-scenarios.md` | AI/Agentic | Vibe-to-Code, Auto-Patching, DB Refactor |
|
|
1352
1360
|
| `guides/patterns/enterprise-migration-scenario.md` | Enterprise | Strangler Fig, Migration paths |
|
|
1353
1361
|
|
|
1354
|
-
| `guides/
|
|
1362
|
+
| `guides/processes/RARV_CYCLE.md` | AI/Agentic | Reason-Act-Reflect-Verify loop |
|
|
1355
1363
|
| `guides/ai/self-healing-summary.md` | AI/Agentic | Self-healing architecture & loops |
|
|
1356
1364
|
| `guides/languages/js-ts-nodejs.md` | Python/Node/React | Swarms, Orchestration, A2A Protocol |
|
|
1357
1365
|
| `guides/patterns/autonomous-swarm-patterns.md` | AI/Agentic | Self-organizing Swarm Patterns |
|
|
@@ -1372,7 +1380,7 @@ Or activate the swarm skill explicitly:
|
|
|
1372
1380
|
|
|
1373
1381
|
| `guides/ops/compliance-audit.md` | Compliance & Audit | GDPR, SOC2 logging, Privacy Engineering |
|
|
1374
1382
|
| `guides/ops/troubleshooting-guide.md` | Ops | Debugging, Root Cause, Recovery |
|
|
1375
|
-
| `guides/
|
|
1383
|
+
| `guides/ai/self-healing-summary.md` | Ops | Automated recovery patterns |
|
|
1376
1384
|
|
|
1377
1385
|
| `guides/ai/ai-agentic.md` | AI/Agentic | RARV, SDD lifecycle, Memory Architecture, MCP config |
|
|
1378
1386
|
| `guides/architecture/microservices.md` | Microservices | Bounded contexts, event-driven, contract testing |
|
|
@@ -1394,12 +1402,12 @@ Or activate the swarm skill explicitly:
|
|
|
1394
1402
|
### Subject-Specific Guides
|
|
1395
1403
|
| Topic | Guide |
|
|
1396
1404
|
|---|---|
|
|
1397
|
-
| **Product** | `guides/product-requirements.md` (PRD/Spec), `guides/strategic-analysis.md` (Strategy) |
|
|
1398
|
-
| **Architecture** | `guides/critical-systems-arch.md`, `guides/event-driven-architecture.md` |
|
|
1399
|
-
| **Integration** | `guides/knowledge-integration.md`, `guides/no-code-integration.md`, `guides/api-standards.md` |
|
|
1400
|
-
| **Agents** | `guides/actor-agent-frameworks.md`, `guides/autonomous-swarm-patterns.md`, `guides/agent-communication.md` |
|
|
1401
|
-
| **UI/UX** | `guides/visual-design-system.md`, `guides/a2ui-protocols.md`, `guides/agent-ui.md` |
|
|
1402
|
-
| **Lifecycle** | `guides/production-health.md`, `guides/beyond-llms.md` |
|
|
1405
|
+
| **Product** | `guides/planning/product-requirements.md` (PRD/Spec), `guides/planning/strategic-analysis.md` (Strategy) |
|
|
1406
|
+
| **Architecture** | `guides/architecture/critical-systems-arch.md`, `guides/architecture/event-driven-architecture.md` |
|
|
1407
|
+
| **Integration** | `guides/processes/knowledge-integration.md`, `guides/principles/no-code-integration.md`, `guides/architecture/api-standards.md` |
|
|
1408
|
+
| **Agents** | `guides/ai/actor-agent-frameworks.md`, `guides/patterns/autonomous-swarm-patterns.md`, `guides/ai/agent-communication.md` |
|
|
1409
|
+
| **UI/UX** | `guides/principles/visual-design-system.md`, `guides/ai/a2ui-protocols.md`, `guides/ai/agent-ui.md` |
|
|
1410
|
+
| **Lifecycle** | `guides/ops/production-health.md`, `guides/ai/beyond-llms.md` |
|
|
1403
1411
|
| **Industry** | `guides/industry/engineering-standards.md`, `guides/industry/global-standards.md`, `guides/industry/telecom-networks.md` |
|
|
1404
1412
|
|
|
1405
1413
|
---
|
|
@@ -1407,7 +1415,7 @@ Or activate the swarm skill explicitly:
|
|
|
1407
1415
|
## 27. Troubleshooting
|
|
1408
1416
|
|
|
1409
1417
|
**Agent ignores AGENTS.md:**
|
|
1410
|
-
- Run `setup-context.sh` to create tool-specific symlinks
|
|
1418
|
+
- Run `agents/scripts/setup-context.sh` to create tool-specific symlinks
|
|
1411
1419
|
- For Cursor: verify `.cursorrules` file exists (symlink created by setup script)
|
|
1412
1420
|
- For Claude Code: verify `.claude/CLAUDE.md` exists
|
|
1413
1421
|
|
|
@@ -1429,7 +1437,7 @@ Or activate the swarm skill explicitly:
|
|
|
1429
1437
|
|
|
1430
1438
|
**Agent makes architecture decisions without asking:**
|
|
1431
1439
|
- Add to AGENTS.md Human-in-the-Loop section: "Architecture changes require human approval"
|
|
1432
|
-
- Check `CONSTITUTION.md` — Article
|
|
1440
|
+
- Check `CONSTITUTION.md` — Article VIII should cover this
|
|
1433
1441
|
|
|
1434
1442
|
**Context window too large / slow responses:**
|
|
1435
1443
|
- Use `context_cost: low` skills for routine tasks
|
|
@@ -1442,8 +1450,8 @@ Or activate the swarm skill explicitly:
|
|
|
1442
1450
|
|
|
1443
1451
|
*See README.md for quick reference.*
|
|
1444
1452
|
*See skills/00-index.md for complete skills registry with installation instructions.*
|
|
1445
|
-
*See agents/skills/brain/
|
|
1446
|
-
*See agents/skills/brain/README.md
|
|
1453
|
+
*See agents/skills/brain/loki-mode.skill.md for Loki Mode multi-agent orchestration.*
|
|
1454
|
+
*See agents/skills/brain/README.md for complete brain documentation.*
|
|
1447
1455
|
|
|
1448
1456
|
|
|
1449
1457
|
---
|