Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/synaptixs/spine/claude-mdgit clone --depth 1 https://github.com/synaptixs/spineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/synaptixs/spine/claude-md)<a href="https://agentmods.dev/instructions/synaptixs/spine/claude-md"><img src="https://agentmods.dev/badge/instructions/synaptixs/spine/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02228 | $0.02228 |
| Opus 5 | $0.01114 | $0.01114 |
| Sonnet 5 | $0.00446 | $0.00446 |
| Haiku 4.5 | $0.00223 | $0.00223 |
Grade A, and why
spine CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spine — working on this repo
Guidance for agents/humans building on this codebase. For using Spine from Claude Code see CLAUDE_GUIDE.md; for PR/branch mechanics and the quality gate see CONTRIBUTING.md; for deploy/env see OPERATIONS.md.
Naming: the product is Spine; the package, import, and CLI stay orchestrator
(PyPI: synaptixs-spine). Use "Spine" in docs and prose, orchestrator in commands.
The knowledge base understand writes is episteme/ (was memory-bank/) — knowledge
grounded in evidence vs doxa, opinion. The same brand/identifier split applies: the
directory is episteme, but the published identifiers keep their names —
read_memory_bank (MCP), GET /v1/capabilities/memory-bank, ORCHESTRATOR_MEMORY_BANK_DIR,
memory_bank_dir(), and the memory-bank/ SDLC artifact-key prefix. Don't rename those
casually; they're contracts. Get the dir from understand.BANK_DIRNAME /
memory_bank_dir() (writes) or existing_bank_dir() (reads — falls back to a legacy
memory-bank/), never a literal.
Layout — where things live
| Package | What it owns |
|---|---|
pkg/ |
The PKG (Product Knowledge Graph) — the source of truth. facts.py = the universal vocabulary (NodeKind/EdgeKind/Node/Edge/FactBatch — includes the Doc node + MENTIONS edge from doc ingestion); extractor.py dispatches per-suffix to language front-ends; store.py = query layer (incl. docs_for/mentions_of); docs.py = the deterministic doc→symbol binder, doc_source.py reads docs (md/rst/txt/PDF, section-split), doc_link.py = the link_docs post-pass (Doc nodes + MENTIONS) + drift; overview.py = bounded view for UIs; persistence.py = commit-keyed cache; export.py/rdf.py = projections |
knowledge/ |
Synthesis on top of the PKG — understand.py (→ episteme/*.md), current_state.py (state, two lenses, incl. the Documentation section; runs link_docs as a post-pass), renderers.py |
registry/ |
FastAPI service + the operator web UI (registry/api/web/) |
sdlc/ |
The feature/run pipeline (largest package) |
catalog/, intake/, agentic/, personas/, evals/ |
profiling, sources→intents, the codegen tool-use loop, personas, measurement |
cli/ |
Every command surface — one module per help panel, sdlc.py and pkg.py on their own; _app.py holds the root app and panels, _common.py the shared helpers |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +36 tokens per session 426bb7768a10
- 4d ago First seen · 113 lines · 2,192 tokens per session scan A 487e0dfe436f
spine CLAUDE.md is an instructions file published in the GitHub repository synaptixs/spine (8 stars, last pushed today), licensed MIT. It adds 2,228 tokens to every session, about $0.0111 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
mcp-devtools CLAUDE.md
Claude Code instructions for sammcj/mcp-devtools, covering claude.md, commands, build and run, testing and code quality.
matryca-plumber AGENTS.md
AGENTS.md instructions for MarcoPorcellato/matryca-plumber, covering agents.md — matryca plumber instruction router, audience map, instruction loading strategy, always-on working agreements and rule and skill routing.
pydantic-ai-todo CLAUDE.md
Instructions for vstorm-co/pydantic-ai-todo, covering claude.md, what this project is, commands, structure and core pattern.
matryca-plumber CLAUDE.md
Claude Code instructions for MarcoPorcellato/matryca-plumber, covering code audit — code intelligence, always do, never do, resources and cli.
tokenjam AGENTS.md
AGENTS.md instructions for Metabuilder-Labs/tokenjam, covering agents.md — tokenjam and quick rules for agents that don't read claude.md.
patchloom AGENTS.md
AGENTS.md instructions for patchloom/patchloom, covering agents.md, project overview, dev commands, git hygiene and release prs (release-please).