RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Configs/AGENTS.md/u9401066/nsforge-mcp

AGENTS.md

AGENTS.md
AGENTS.mdroot

Quality

89/100

Scores the file, not the repository.

Length

411 words

8 headings · 1 code blocks

Repository

4

— · pushed 27 days ago

Last changed

3 days ago

First indexed 3 days ago.
u9401066/nsforge-mcp/AGENTS.mdRawGitHub
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 

Commands it names

  • python scripts/check.py
  • python scripts/check.py --json
  • python scripts/check.py --gates lint,type,test
  • mypy
  • uv run ...
  • python scripts/gen_capabilities.py

Sections

  • NSForge Agent Harness
  • Goal
  • North Star
  • Working Style
  • Ground Truth: one command
  • Repo Layout (DDD)
  • Guardrails
  • Related Files

What it covers

code-stylearchitecturesecuritydo-notagent-behaviour

Stack — with the evidence

python

(1.00)

pytest

(0.70)

ruff

(0.70)

github-actions

(0.60)

Format

AGENTS.md

A plain-markdown README for coding agents, deliberately unopinionated: no frontmatter, no globs, no vendor keys. That minimalism is why it became the one file a dozen different agents will read, and why it carries the least per-file targeting power of any format here.

What the corpus says about it

Repository

Owner
u9401066
Language
—
License
—
Archived
no

All configs in this repo

Also in u9401066/nsforge-mcp

Diff this repo’s formats

One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?

The other instruction files in this repository
RepositoryFormatStackCoversScoreChanged
u9401066/nsforge-mcp.clinerules/00-project.md · 4Cline rulespythonpytest+2testlint-formatstylearch+181/1003 days ago
u9401066/nsforge-mcp.clinerules/10-python.md · 4Cline rulespythonpytest+2setuptestlint-formatstyle+183/1003 days ago
u9401066/nsforge-mcp.clinerules/40-release.md · 4Cline rulespythonpytest+2lint-formatdeploymentdo-not51/1003 days ago
u9401066/nsforge-mcp.github/copilot-instructions.md · 4Copilot instructionspythonpytest+2setuptestlint-formatgit+285/1003 days ago
u9401066/nsforge-mcpCLAUDE.md · 4CLAUDE.mdpythonpytest+2setuptestlint-formatgit+281/1003 days ago
Diff against .clinerules/00-project.md Diff against .clinerules/10-python.md Diff against .clinerules/40-release.md Diff against .github/copilot-instructions.md Diff against CLAUDE.md

Similar configs

Same format, overlapping stack, ranked by quality.

Same format, overlapping stack, ranked by quality
RepositoryFormatStackCoversScoreChanged
vllm-project/vllmAGENTS.md · 88kAGENTS.mdpythonpytorch+3setuptestlint-formatstyle+5100/1003 days ago
OnlyTerp/prompt-cache-skillsAGENTS.md · 112AGENTS.mdpythongithub-actionssetupbuildtestlint-format+5100/1003 days ago
n8n-io/n8npackages/@n8n/agents/AGENTS.md · 199kAGENTS.mdtypescriptlangchain+16buildteststylearch+3100/1003 days ago
unoplat/unoplat-code-confluenceunoplat-code-confluence-frontend/AGENTS.md · 95AGENTS.mdtypescriptpython+14setupbuildtestlint-format+6100/1002 days ago
SkeneTechnologies/skene-cookbookAGENTS.md · 51AGENTS.mdpythoneslint+4setupbuildtestlint-format+7100/1002 days ago
netdata/netdatasrc/go/plugin/ibm.d/AGENTS.md · 80kAGENTS.mddockerinfrastructure+7buildtestlint-formatarch+399/1003 days ago
unoplat/unoplat-code-confluenceunoplat-code-confluence-query-engine/AGENTS.md · 95AGENTS.mdtypescriptpython+13setupbuildtestlint-format+598/1002 days ago
alibaba/opc-starterAGENTS.md · 87AGENTS.mdnodepython+10setupbuildtestlint-format+597/1003 days ago
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