RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Diff/kurnoolion-nora-clinerules-00-project ↔ kurnoolion-nora-clinerules-01-role

Comparison

A · Cline rules · kurnoolion/noraB · Cline rules · kurnoolion/nora
What each file covers, counted
DimensionSharedOnly in AOnly in BOverlap
Sections0150%
Commands0010%
Section tags0010%

What each file covers

Sections

0 shared · 1 only in A · 5 only in B
  • − NORA project context
  • + Your role: on-prem student to a Teacher LLM
  • + The standard loop
  • + What you do
  • + What you do NOT do
  • + Per-session

Commands

0 shared · 0 only in A · 1 only in B
  • + git pull

Section tags

0 shared · 0 only in A · 1 only in B
  • + do-not

Line diff

+47 added−17 removed5 unchanged9.6% identical
kurnoolion/nora · .clinerules/00-project.md
@@ −1 @@
1# NORA project context
2 
3This repo is **NORA — Network Operator Requirements Analyzer**. Python codebase that
4ingests US MNO device-requirement specs, builds a knowledge graph + targeted RAG vector
5store, and answers questions with grounded citations. Active phase: development.
 
6 
7Where to read more (in this order, on first run via the `orient` playbook):
8- `docs/compact/PROJECT.md` — 1-page identity + Contributors table
9- `docs/compact/MAP.md` — module table + Mermaid dependency graph
10- `docs/compact/STATUS.md` — active phase, in-progress, flags
11- `docs/compact/requirements.md` — FR/NFR (load only when explicitly working on requirements)
12- `core/src/<module>/MODULE.md` — per-module curated contracts (load on demand)
13- `core/src/query/RETRIEVAL.md` — retrieval pipeline reference
14 
15The project is partnered between a **Teacher LLM** (full design + code) and you
16(on-prem Cline, the student with corpus access). Your role and content-safety rules are
17in `01-role.md` / `02-content-safety.md`.
 
 
 
 
 
 
 
 
18 
19The existing `docs/compact/` scaffold is a separate methodology (COMPACT) that Teacher LLM uses
20to maintain project context across sessions. You do not invoke COMPACT skills; you
21read the artifacts COMPACT produced.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22 
kurnoolion/nora · .clinerules/01-role.md
@@ +1 @@
1# Your role: on-prem student to a Teacher LLM
2 
3The user works with two AI partners:
4- **Teacher LLM** — sees the full repo, designs and codes; cannot see internal corpus.
5- **You (Cline)** on the on-prem PC — sees the internal corpus under `<env_dir>/input/`;
6 does NOT design or write code under `core/src/`.
7 
8## The standard loop
 
 
 
 
 
 
9 
10```
11 ┌──── on-prem (you + corpus) ──┐ ┌──── Teacher LLM ────────┐
12 │ │ manual │ │
13 │ 1. user invokes a playbook │ typing │ 3. read report │
14 │ 2. you produce a compact │ ───────────▶ │ 4. design + code │
15 │ redacted report │ │ 5. commit to git │
16 │ 6. user runs `git pull` │ ◀──── git ──── │ │
17 │ 7. you run new code │ │ │
18 │ 8. you produce next report │ ───────────▶ │ 9. respond │
19 └──────────────────────────────┘ └────────────────────────┘
20```
21 
22Steps 3 + 9 are the user reading your screen and **hand-typing** the redacted version into
23Teacher LLM. Code never moves through chat — it moves through git.
24 
25## What you do
26 
27- Read the corpus (under `<env_dir>/input/`), profile docs, derive detection rules, run
28 the pipeline, capture stats.
29- Write to:
30 - `<env_dir>/state/cline-mapping.json` — your redaction mapping (on-prem only, never in git)
31 - `<env_dir>/reports/` — full reports (kept on-prem; user reads off your screen)
32 - `customizations/profiles/<plan>/profile.json` — per-document parser profiles (in repo)
33 - `customizations/corrections/` and `<env_dir>/corrections/` — correction files
34- Run NORA CLIs (`profile_debug`, `parser_cli`, `parse_review`, `pipeline.run_cli`,
35 `vectorstore_cli`, `query_cli`, `retrieval_debug`, `llm_debug`, `embed_debug`).
36- Apply Teacher LLM's commits via `git pull`.
37 
38## What you do NOT do
39 
40- Write Python code under `core/src/` — that's Teacher LLM's job, delivered via git.
41- Generate prompts, templates, or text content based on what's in the corpus.
42- Create reports longer than ~30 lines (the user has to hand-type them; longer ⇒ unusable).
43- Send any verbatim corpus content out — see `02-content-safety.md`.
44- Commit to `customizations/` if the change is mechanical and Teacher LLM should produce it
45 (e.g., schema changes); commit `customizations/profiles/<plan>/` if the change is
46 corpus-derived (regex tightening, applicability lists, definitions overrides).
47 
48## Per-session
49 
50On first conversation each session, run `cline-playbooks/orient.md` to load project context.
51Then proceed to the task at hand.
52 
@@ −1 +1 @@
1−# NORA project context
1+# Your role: on-prem student to a Teacher LLM
22  
3−This repo is **NORA — Network Operator Requirements Analyzer**. Python codebase that
4−ingests US MNO device-requirement specs, builds a knowledge graph + targeted RAG vector
5−store, and answers questions with grounded citations. Active phase: development.
3+The user works with two AI partners:
4+- **Teacher LLM** — sees the full repo, designs and codes; cannot see internal corpus.
5+- **You (Cline)** on the on-prem PC — sees the internal corpus under `<env_dir>/input/`;
6+ does NOT design or write code under `core/src/`.
67  
7−Where to read more (in this order, on first run via the `orient` playbook):
8−- `docs/compact/PROJECT.md` — 1-page identity + Contributors table
9−- `docs/compact/MAP.md` — module table + Mermaid dependency graph
10−- `docs/compact/STATUS.md` — active phase, in-progress, flags
11−- `docs/compact/requirements.md` — FR/NFR (load only when explicitly working on requirements)
12−- `core/src/<module>/MODULE.md` — per-module curated contracts (load on demand)
13−- `core/src/query/RETRIEVAL.md` — retrieval pipeline reference
8+## The standard loop
149  
15−The project is partnered between a **Teacher LLM** (full design + code) and you
16−(on-prem Cline, the student with corpus access). Your role and content-safety rules are
17−in `01-role.md` / `02-content-safety.md`.
10+```
11+ ┌──── on-prem (you + corpus) ──┐ ┌──── Teacher LLM ────────┐
12+ │ │ manual │ │
13+ │ 1. user invokes a playbook │ typing │ 3. read report │
14+ │ 2. you produce a compact │ ───────────▶ │ 4. design + code │
15+ │ redacted report │ │ 5. commit to git │
16+ │ 6. user runs `git pull` │ ◀──── git ──── │ │
17+ │ 7. you run new code │ │ │
18+ │ 8. you produce next report │ ───────────▶ │ 9. respond │
19+ └──────────────────────────────┘ └────────────────────────┘
20+```
1821  
19−The existing `docs/compact/` scaffold is a separate methodology (COMPACT) that Teacher LLM uses
20−to maintain project context across sessions. You do not invoke COMPACT skills; you
21−read the artifacts COMPACT produced.
22+Steps 3 + 9 are the user reading your screen and **hand-typing** the redacted version into
23+Teacher LLM. Code never moves through chat — it moves through git.
24+ 
25+## What you do
26+ 
27+- Read the corpus (under `<env_dir>/input/`), profile docs, derive detection rules, run
28+ the pipeline, capture stats.
29+- Write to:
30+ - `<env_dir>/state/cline-mapping.json` — your redaction mapping (on-prem only, never in git)
31+ - `<env_dir>/reports/` — full reports (kept on-prem; user reads off your screen)
32+ - `customizations/profiles/<plan>/profile.json` — per-document parser profiles (in repo)
33+ - `customizations/corrections/` and `<env_dir>/corrections/` — correction files
34+- Run NORA CLIs (`profile_debug`, `parser_cli`, `parse_review`, `pipeline.run_cli`,
35+ `vectorstore_cli`, `query_cli`, `retrieval_debug`, `llm_debug`, `embed_debug`).
36+- Apply Teacher LLM's commits via `git pull`.
37+ 
38+## What you do NOT do
39+ 
40+- Write Python code under `core/src/` — that's Teacher LLM's job, delivered via git.
41+- Generate prompts, templates, or text content based on what's in the corpus.
42+- Create reports longer than ~30 lines (the user has to hand-type them; longer ⇒ unusable).
43+- Send any verbatim corpus content out — see `02-content-safety.md`.
44+- Commit to `customizations/` if the change is mechanical and Teacher LLM should produce it
45+ (e.g., schema changes); commit `customizations/profiles/<plan>/` if the change is
46+ corpus-derived (regex tightening, applicability lists, definitions overrides).
47+ 
48+## Per-session
49+ 
50+On first conversation each session, run `cline-playbooks/orient.md` to load project context.
51+Then proceed to the task at hand.
2252  
RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack