spc CLAUDE.md

Project instructions for spc that require tracking work, decisions, dependencies, and blockers in a state-memory graph.

In plain words
What is it for?
Use it to start tracked sessions, find the next task and blockers, record decisions, and trace what depends on a task.
Why use it?
It helps keep project progress and reasoning visible across sessions instead of relying only on the current conversation.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/putervision/spc/claude-md
Clone the repo
git clone --depth 1 https://github.com/putervision/spc
Per session 1,755 This file is loaded in full into every session.
When invoked 1,755 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin 94% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01755 $0.01755
Opus 5 $0.00877 $0.00877
Sonnet 5 $0.00351 $0.00351
Haiku 4.5 $0.00176 $0.00176

Measured 2d ago against content hash 94614c966b2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

spc CLAUDE.md scanned grade B with 1 finding 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 2d ago.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

* **Google Antigravity (`~/.gemini/config/config.json`)**: Add these rules to your `"globalPermissionGrants"` -> `"allow"` list:
Origin

This is a copy

94% identical to state-memory-mcp copilot-instructions.md — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

State Memory (state-memory-mcp)

This project tracks workflow state, tasks, design decisions, and blockers using state-memory-mcp with project slug "spc".

1. Priority Order

Before doing any coding or investigation:

  1. manage_sessions(action: "start") — Start a tracking session for full change attribution.
  2. get_analytics(action: "summary") — Run to understand current project state, active branches, and overall progress.
  3. manage_tasks(action: "next") — Query prioritized runnable tasks.
  4. manage_tasks(action: "find_blockers") — Identify any active blockers preventing progress.
  5. manage_nodes(action: "list") — Find pending tasks, past decisions, or milestones.
  6. query_graph(action: "trace") — Trace what depends on or blocks a task.

2. When to Write to the Graph

You MUST update the graph as you work:

  • Starting a session: Always call manage_sessions(action: "start", agent_id: "my-agent") to track all mutations under a unique session.
  • Starting a new task: Create a node with manage_nodes(action: "create", type: "task", title: "...", session_id: session_id).
  • Making a design or implementation decision: Document it with manage_nodes(action: "create", type: "decision", title: "...", metadata: { "rationale": "..." }, session_id: session_id).
  • Encountering a blocker: Record the blocker with manage_nodes(action: "create", type: "blocker", title: "...", session_id: session_id) and connect it using manage_edges(action: "add", type: "blocks", source_id: blocker_id, target_id: task_id, session_id: session_id).
  • Adding observation notes: Atomically log notes using manage_nodes(action: "add_note", text: "...", attach_to: node_id).
  • Batch updates: Bulk update tasks/nodes using manage_nodes(action: "batch_update", ids: ["..."], status: "done").
  • Completing a task: Update status to done using manage_tasks(action: "complete", task_id: task_id) or manage_nodes(action: "update", id: task_id, status: "done").
  • Creating/generating a new file: Create an artifact node with manage_nodes(action: "create", type: "artifact", title: "...", session_id: session_id) and connect it using manage_edges(action: "add", type: "produces", source_id: task_id, target_id: artifact_id).

Read the full file on GitHub · 77 lines

Changes

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.

  1. 2d ago First seen · 77 lines · 1,755 tokens per session scan B 94614c966b2c

Subscribe to this mod's changes

spc CLAUDE.md is an instructions file published in the GitHub repository putervision/spc (39 stars, last pushed 11d ago), licensed MIT. It adds 1,755 tokens to every session, about $0.0088 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 94% identical to state-memory-mcp copilot-instructions.md, differing in 12 lines, and is treated as a copy.