| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 5 | 3 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 0 | 1 | 1 | 0% |
What each file covers
Sections
0 shared · 5 only in A · 3 only in B- − Claude Integration Entry
- − Startup (every conversation)
- − Slash Commands
- − Skills
- − Validate
- + Gemini Integration Entry
- + Startup
- + Review
Commands
neither file has anySection tags
0 shared · 1 only in A · 1 only in B- − agent-behaviour
- + git-pr
Line diff
KbWen/agentic-os · CLAUDE.md
@@ −1 @@
1@AGENTS.md
2
3# Claude Integration Entry
4
5`AGENTS.md` is auto-injected above via `@import` — governance rules, gates, and state model are already in context. This file only adds Claude-specific dispatch. **Do NOT duplicate rules from AGENTS.md here.**
6
7## Startup (every conversation)
8
91. **At the start of a task, enter the governed flow in `AGENTS.md` before any file edit or completion claim — decide up front, not at the edit moment. No silent direct edits.**
102. Classify task scope from the user's message:
11 - `tiny-fix` (< 3 files, no semantic change) → skip to Step 5.
12 - `quick-win` (1–2 modules, clear scope) → read SSoT (Step 3), skip Step 4.
13 - `feature` / `architecture-change` / `hotfix` / uncertain → continue.
143. Read `.agentcortex/context/current_state.md` (SSoT). *(Skip for tiny-fix.)*
154. Read `.agent/rules/engineering_guardrails.md`. *(Skip for tiny-fix and quick-win.)*
165. If `.agentcortex/context/work/<worklog-key>.md` exists, read to resume. *(Skip for tiny-fix.)*
17
18Token budget rationale: conditional loading saves ~5,000 tokens for tiny-fix, ~3,500 tokens for quick-win. Full mechanics: `AGENTS.md §vNext State Model`.
19
20## Slash Commands
21
22`/command` dispatches via `.claude/commands/<command>.md` → canonical workflow at `.agent/workflows/<command>.md`.
23
24## Skills
25
26Skill metadata: `.agent/skills/*`. Full instructions: `.agents/skills/*/SKILL.md`. Activation and cache policy: `AGENTS.md §Skill Safety & Precedence` and `§Shared Phase Contracts`.
27
28## Validate
29
30Run `.agentcortex/bin/validate.sh` (bash) or `.agentcortex/bin/validate.ps1` (PowerShell).
31
KbWen/agentic-os · GEMINI.md
@@ +1 @@
1@AGENTS.md
2
3# Gemini Integration Entry
4
5`AGENTS.md` is the shared governance and review source of truth for this repository. This file only adapts Gemini CLI to that shared context; do not duplicate rules here.
6
7## Startup
8
91. **At the start of a task, enter the governed flow in `AGENTS.md` before any file edit or completion claim — decide up front, not at the edit moment. No silent direct edits.**
102. Use `/memory show` when you need to inspect the active Gemini context.
113. Use `/memory refresh` after this file or `AGENTS.md` changes during an active session.
12
13## Review
14
15Use `AGENTS.md ## Review guidelines` for review priorities. For phase/gate details, read the referenced `.agent/workflows/*.md` files instead of inferring process from this adapter.
16
@@ −1 +1 @@
11 @AGENTS.md
22
3−# Claude Integration Entry
3+# Gemini Integration Entry
44
5−`AGENTS.md` is auto-injected above via `@import` — governance rules, gates, and state model are already in context. This file only adds Claude-specific dispatch. **Do NOT duplicate rules from AGENTS.md here.**
5+`AGENTS.md` is the shared governance and review source of truth for this repository. This file only adapts Gemini CLI to that shared context; do not duplicate rules here.
66
7−## Startup (every conversation)
7+## Startup
88
99 1. **At the start of a task, enter the governed flow in `AGENTS.md` before any file edit or completion claim — decide up front, not at the edit moment. No silent direct edits.**
10−2. Classify task scope from the user's message:
11− - `tiny-fix` (< 3 files, no semantic change) → skip to Step 5.
12− - `quick-win` (1–2 modules, clear scope) → read SSoT (Step 3), skip Step 4.
13− - `feature` / `architecture-change` / `hotfix` / uncertain → continue.
14−3. Read `.agentcortex/context/current_state.md` (SSoT). *(Skip for tiny-fix.)*
15−4. Read `.agent/rules/engineering_guardrails.md`. *(Skip for tiny-fix and quick-win.)*
16−5. If `.agentcortex/context/work/<worklog-key>.md` exists, read to resume. *(Skip for tiny-fix.)*
10+2. Use `/memory show` when you need to inspect the active Gemini context.
11+3. Use `/memory refresh` after this file or `AGENTS.md` changes during an active session.
1712
18−Token budget rationale: conditional loading saves ~5,000 tokens for tiny-fix, ~3,500 tokens for quick-win. Full mechanics: `AGENTS.md §vNext State Model`.
13+## Review
1914
20−## Slash Commands
21−
22−`/command` dispatches via `.claude/commands/<command>.md` → canonical workflow at `.agent/workflows/<command>.md`.
23−
24−## Skills
25−
26−Skill metadata: `.agent/skills/*`. Full instructions: `.agents/skills/*/SKILL.md`. Activation and cache policy: `AGENTS.md §Skill Safety & Precedence` and `§Shared Phase Contracts`.
27−
28−## Validate
29−
30−Run `.agentcortex/bin/validate.sh` (bash) or `.agentcortex/bin/validate.ps1` (PowerShell).
15+Use `AGENTS.md ## Review guidelines` for review priorities. For phase/gate details, read the referenced `.agent/workflows/*.md` files instead of inferring process from this adapter.
3116
