agentmods.dev

Senti-MCP: Instructions file for Claude Code

CLAUDE.md

Senti-MCP CLAUDE.md is an instructions file for Claude Code from Koniverse/Senti-MCP. It costs 442 tokens per session, scanned A, original, MIT.

Repository-specific instructions for Claude Code in Senti-MCP, including documentation and sprint-file rules. AGENTS.md is the main instruction file for the project.

In plain words
What is it for?
Working on the Senti-MCP codebase, using its documentation tools, and updating sprint status correctly.
Why use it?
They prevent conflicting instructions and explain where the project’s current work and documentation are maintained.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Koniverse/Senti-MCP's own configuration. It tells Claude Code how to work on Senti-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Senti-MCP configures →

not rated 2repo changed 1mo ago A scan 442 tokens original MIT
View source ↗ Koniverse/Senti-MCP
Reuse

Borrowing it

Nothing to install: this file belongs to Koniverse/Senti-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Koniverse/Senti-MCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Koniverse/Senti-MCP

Made for: Claude Code.

Wrote 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.

agentmods badge for Senti-MCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/koniverse/senti-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/koniverse/senti-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/koniverse/senti-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/koniverse/senti-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Senti-MCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/koniverse/senti-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/koniverse/senti-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 442 This file is loaded in full into every session.
When invoked 442 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 5.1 $0.00442 $0.00442
Opus 5.5 $0.00177 $0.00177
Sonnet 5.5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 1mo ago against content hash bd30d18cba37, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Senti-MCP 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 1mo 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.

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.

CLAUDE.md · 32 lines

What it actually says

CLAUDE.md — senti-mcp-server

This project uses AGENTS.md as the single source of truth for all AI instructions — project purpose, repo structure, conventions, skill catalog, security invariants, and the documentation map. Read it first. On any conflict, AGENTS.md wins.

Koni-Docs Integration

koni-docs: plugins: [] docs_path: docs/ active_sprint: sprint-2026-W41 version_file: VERSION

Repo-specific notes for Claude Code

  • This repo keeps no Active Context block. Never write one. Do not add an ## Active Context section to this file, do not create .active-context.md, and do not restore the <!-- koni-docs:auto-update --> markers — neither koni-docs Pattern A nor Pattern B is in use here (CONTEXT D7). This overrides the koni-docs skill's §4 trigger points (T1–T7) and the Active Context line in its §3c checklist. What is in flight lives in the sprint file and docs/sprints/STATUS.md — read those, and keep them current instead.
  • npm run sets cwd to the package root. agile:status and agile:validate resolve --docs-path docs/ correctly regardless of where you invoke them from — but a bare npx koni-docs … does not. Run those from the repo root.
  • .claude/skills/koni-docs is a symlink into .agents/skills/koni-docs. Read through it freely; do not write through it. See AGENTS.md §Skills.
  • docs/superpowers/ is not legacy. Superpowers produces the spec and the plan; koni-docs standardizes the outcome into epics, stories, and a changelog. Both stay.
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. 1mo ago Changed bd30d18cba37
  2. 1mo ago Changed 76388c6ca158
  3. 1mo ago Changed 9bbec948ed82
  4. 1mo ago Changed 1b7a162afcda
  5. 2mo ago Changed 539c1b4bc6f2
  6. 2mo ago First seen · 32 lines · 442 tokens per session scan A cd2ba572d514

Subscribe to this mod's changes

Senti-MCP CLAUDE.md is an instructions file published in the GitHub repository Koniverse/Senti-MCP (2 stars, last pushed 8d ago), licensed MIT. It adds 442 tokens to every session, about $0.0018 per session on Opus 5.5. 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.

Related

Senti-MCP CLAUDE.md compared with instructions from other repositories

Senti-MCP CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Senti-MCP CLAUDE.mdKoniverse/Senti-MCPInstructions file28d agoMITA442Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode