RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Diff/u9401066-nsforge-mcp-agents ↔ u9401066-nsforge-mcp-clinerules-10-python

Comparison

A · AGENTS.md · u9401066/nsforge-mcpB · Cline rules · u9401066/nsforge-mcp
What each file covers, counted
DimensionSharedOnly in AOnly in BOverlap
Sections0850%
Commands33430%
Section tags23325%

What each file covers

Sections

0 shared · 8 only in A · 5 only in B
  • − NSForge Agent Harness
  • − Goal
  • − North Star
  • − Working Style
  • − Ground Truth: one command
  • − Repo Layout (DDD)
  • − Guardrails
  • − Related Files
  • + Python Rules (uv / ruff / mypy / pytest)
  • + Environment
  • + Architecture Guardrails
  • + Validation Gates
  • + Discipline

Commands

3 shared · 3 only in A · 4 only in B
  • − python scripts/check.py --json
  • − python scripts/check.py --gates lint,type,test
  • − mypy
  • + uv run ruff check .
  • + uv run ruff format --check .
  • + uv run mypy src --ignore-missing-imports
  • + uv run pytest
  •   python scripts/check.py
  •   uv run ...
  •   python scripts/gen_capabilities.py

Section tags

2 shared · 3 only in A · 3 only in B
  • − architecture
  • − security
  • − agent-behaviour
  • + setup
  • + test
  • + lint-format
  •   code-style
  •   do-not

Line diff

+25 added−64 removed8 unchanged11.1% identical
u9401066/nsforge-mcp · AGENTS.md
@@ −1 @@
1# NSForge Agent Harness
 
 
 
 
 
 
2 
3Workspace instructions for autonomous agents (Copilot, Cline, Codex, OpenHands,
4Hermes, …) working in the **Neurosymbolic Forge (NSForge)** repository.
5 
6## Goal
 
 
7 
8Help build and operate NSForge — an MCP server that turns *concepts* into
9verifiable, traceable *entities* (symbols → derivations → algorithms). The AI
10orchestrates; deterministic tools reify. See
11`docs/reification-ladder-direction.md` for the north star.
12 
13## North Star
 
 
 
 
 
 
14 
15> Every symbol / equation / value / line of code in a final result must have a
16> tool call as its "birth certificate" (provenance). The AI must not hand-derive
17> any of them.
18 
19Success = the amount the AI computes by hand approaches zero.
20 
21## Working Style
22 
23- Use Traditional Chinese unless the user asks otherwise.
24- Prefer exact file paths, command output summaries, and verification results.
25- Offload mechanical/deterministic steps (symbolic calculation, simplification,
26 code generation) to tools — do not hand-derive formulas.
27- When changing behavior, add a focused regression test under `tests/`.
28 
29## Ground Truth: one command
30 
31Before and after changes, verify against the green baseline:
32 
33```bash
34python scripts/check.py # all gates
35python scripts/check.py --json # machine-readable summary (for agents)
36python scripts/check.py --gates lint,type,test # subset
37```
38 
39Gates: lint, format, type, import, manifest, test, bench, generic, provenance, harness, diff. Exit code 0 = green.
40(bench = derivation-correctness of `benchmarks/*.json` through the L3 orchestrator;
41generic = arbitrary unseen compositions derive correctly, proving NSForge is a
42derivation *calculus*, not a hand-built formula library; provenance = every
43benchmark derivation carries a complete tool-provenance ledger, no hand-derived leaks;
44harness = the harness self-checks its own invariants — version single-source,
45self-describing tools, and gate/doc parity — so agents can trust the signal.)
46 
47## Repo Layout (DDD)
48 
49- `src/nsforge/domain/`: pure domain models/value objects (no I/O)
50- `src/nsforge/application/`: use-cases / orchestration
51- `src/nsforge/infrastructure/`: adapters (sympy engine, formula sources, file I/O)
52- `src/nsforge_mcp/`: MCP tool layer + server wiring (`server.py`, `tools/`)
53- `docs/agent/capabilities.json`: machine-readable tool manifest (self-describing)
54 
55## Guardrails
56 
57- Keep `src/nsforge/domain` free of I/O and infrastructure imports.
58- Do not weaken `mypy` strict or skip gates just to make checks pass.
59- Prefer `uv run ...` so tools use the project venv.
60- Avoid destructive git ops (`reset --hard`, `clean -fdx`) unless asked.
61- Never commit secrets or generated outputs (`dist/`, `.venv/`, `data/`).
62- After adding/removing an `@mcp.tool`, regenerate the manifest:
63 `python scripts/gen_capabilities.py`.
64 
65## Related Files
66 
67- `docs/reification-ladder-direction.md` — architecture direction
68- `scripts/check.py` — verification harness (ground truth)
69- `scripts/gen_capabilities.py` — capability manifest generator
70- `.github/copilot-instructions.md` — Copilot rules
71- `memory-bank/activeContext.md` — current focus
72 
u9401066/nsforge-mcp · .clinerules/10-python.md
@@ +1 @@
1---
2paths:
3 - "src/**/*.py"
4 - "tests/**/*.py"
5 - "scripts/**/*.py"
6 - "pyproject.toml"
7---
8 
9# Python Rules (uv / ruff / mypy / pytest)
 
10 
11## Environment
12- Use `uv` for running tools (avoid ad-hoc `pip`).
13- Prefer `uv run ...` so checks execute in the right venv and dependency set.
14 
15## Architecture Guardrails
16- Keep `src/nsforge/domain` free of I/O, filesystem access, and infrastructure imports.
17- Put orchestration/side-effects in `src/nsforge/application` or `src/nsforge/infrastructure`.
18- MCP tool wiring lives in `src/nsforge_mcp/` (`server.py`, `tools/`).
19 
20## Validation Gates
21- One command: `python scripts/check.py`
22- Or individually:
23 - Lint: `uv run ruff check .`
24 - Format: `uv run ruff format --check .`
25 - Types: `uv run mypy src --ignore-missing-imports`
26 - Tests: `uv run pytest`
27 
28## Discipline
29- Do not weaken mypy strict or add blanket `# type: ignore` to pass the gate.
30- Add a regression test under `tests/` when fixing a bug.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31- After adding/removing an `@mcp.tool`, regenerate the manifest:
32 `python scripts/gen_capabilities.py`.
 
 
 
 
 
 
 
 
33 
@@ −1 +1 @@
1−# NSForge Agent Harness
1+---
2+paths:
3+ - "src/**/*.py"
4+ - "tests/**/*.py"
5+ - "scripts/**/*.py"
6+ - "pyproject.toml"
7+---
28  
3−Workspace instructions for autonomous agents (Copilot, Cline, Codex, OpenHands,
4−Hermes, …) working in the **Neurosymbolic Forge (NSForge)** repository.
9+# Python Rules (uv / ruff / mypy / pytest)
510  
6−## Goal
11+## Environment
12+- Use `uv` for running tools (avoid ad-hoc `pip`).
13+- Prefer `uv run ...` so checks execute in the right venv and dependency set.
714  
8−Help build and operate NSForge — an MCP server that turns *concepts* into
9−verifiable, traceable *entities* (symbols → derivations → algorithms). The AI
10−orchestrates; deterministic tools reify. See
11−`docs/reification-ladder-direction.md` for the north star.
15+## Architecture Guardrails
16+- Keep `src/nsforge/domain` free of I/O, filesystem access, and infrastructure imports.
17+- Put orchestration/side-effects in `src/nsforge/application` or `src/nsforge/infrastructure`.
18+- MCP tool wiring lives in `src/nsforge_mcp/` (`server.py`, `tools/`).
1219  
13−## North Star
20+## Validation Gates
21+- One command: `python scripts/check.py`
22+- Or individually:
23+ - Lint: `uv run ruff check .`
24+ - Format: `uv run ruff format --check .`
25+ - Types: `uv run mypy src --ignore-missing-imports`
26+ - Tests: `uv run pytest`
1427  
15−> Every symbol / equation / value / line of code in a final result must have a
16−> tool call as its "birth certificate" (provenance). The AI must not hand-derive
17−> any of them.
18− 
19−Success = the amount the AI computes by hand approaches zero.
20− 
21−## Working Style
22− 
23−- Use Traditional Chinese unless the user asks otherwise.
24−- Prefer exact file paths, command output summaries, and verification results.
25−- Offload mechanical/deterministic steps (symbolic calculation, simplification,
26− code generation) to tools — do not hand-derive formulas.
27−- When changing behavior, add a focused regression test under `tests/`.
28− 
29−## Ground Truth: one command
30− 
31−Before and after changes, verify against the green baseline:
32− 
33−```bash
34−python scripts/check.py # all gates
35−python scripts/check.py --json # machine-readable summary (for agents)
36−python scripts/check.py --gates lint,type,test # subset
37−```
38− 
39−Gates: lint, format, type, import, manifest, test, bench, generic, provenance, harness, diff. Exit code 0 = green.
40−(bench = derivation-correctness of `benchmarks/*.json` through the L3 orchestrator;
41−generic = arbitrary unseen compositions derive correctly, proving NSForge is a
42−derivation *calculus*, not a hand-built formula library; provenance = every
43−benchmark derivation carries a complete tool-provenance ledger, no hand-derived leaks;
44−harness = the harness self-checks its own invariants — version single-source,
45−self-describing tools, and gate/doc parity — so agents can trust the signal.)
46− 
47−## Repo Layout (DDD)
48− 
49−- `src/nsforge/domain/`: pure domain models/value objects (no I/O)
50−- `src/nsforge/application/`: use-cases / orchestration
51−- `src/nsforge/infrastructure/`: adapters (sympy engine, formula sources, file I/O)
52−- `src/nsforge_mcp/`: MCP tool layer + server wiring (`server.py`, `tools/`)
53−- `docs/agent/capabilities.json`: machine-readable tool manifest (self-describing)
54− 
55−## Guardrails
56− 
57−- Keep `src/nsforge/domain` free of I/O and infrastructure imports.
58−- Do not weaken `mypy` strict or skip gates just to make checks pass.
59−- Prefer `uv run ...` so tools use the project venv.
60−- Avoid destructive git ops (`reset --hard`, `clean -fdx`) unless asked.
61−- Never commit secrets or generated outputs (`dist/`, `.venv/`, `data/`).
28+## Discipline
29+- Do not weaken mypy strict or add blanket `# type: ignore` to pass the gate.
30+- Add a regression test under `tests/` when fixing a bug.
6231 - After adding/removing an `@mcp.tool`, regenerate the manifest:
6332 `python scripts/gen_capabilities.py`.
64− 
65−## Related Files
66− 
67−- `docs/reification-ladder-direction.md` — architecture direction
68−- `scripts/check.py` — verification harness (ground truth)
69−- `scripts/gen_capabilities.py` — capability manifest generator
70−- `.github/copilot-instructions.md` — Copilot rules
71−- `memory-bank/activeContext.md` — current focus
7233  
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