agentmods.dev

sipcode CLAUDE.md

A set of response rules for the Sipcode project that keeps coding-agent replies short and focused on file changes.

In plain words
What is it for?
It is for showing only changed sections, preferring code and bullets, and giving one clear example when editing or explaining code.
Why use it?
It reduces repeated code, introductions, summaries, and other text that can use tokens without helping with the task.

Instructions file

46 1mo ago A scan 362 tokens original MIT
View the source file Anuj7411/sipcode
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/anuj7411/sipcode/claude-md
Clone the repo
git clone --depth 1 https://github.com/Anuj7411/sipcode
Per session 362 This file is loaded in full into every session.
When invoked 362 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00362 $0.00362
Opus 5 $0.00181 $0.00181
Sonnet 5 $0.00072 $0.00072
Haiku 4.5 $0.00036 $0.00036

Measured 2d ago against content hash 89799c9f93f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sipcode 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 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.

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

Sipcode Output Compression

mode: default — optimizes for: diff edits, no ceremony

the rules below apply to your responses in this project. follow them. they exist so the user pays for code, not for ceremony.

rules (default mode)

  1. diff-only edits. when editing a file, output only the changed hunk plus three lines of context. never paste the full file back when three lines changed. this is the single biggest win.
  2. no preamble. skip "i'll help with that", "sure", "here's what i did". lead with the work. the user can see what you did.
  3. no post-amble. don't summarize what was just shown unless the user explicitly asks for a summary.
  4. code over prose. when the answer is code, the code is the answer. any explanation goes after the code block, not before.
  5. bullets over paragraphs for any list of options, steps, or trade-offs. saves tokens versus flowing prose.
  6. one canonical example, not three. show one good example. skip the exhaustive variants — the user will ask if they want more.
  7. no filler verbs. drop "let me", "i'll go ahead and", "i'm going to". just do the thing.

(installed by sipcode. switch modes with npx sipcode rules --mode <m>. uninstall with npx sipcode rules --uninstall.)

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 · 32 lines · 362 tokens per session scan A 89799c9f93f2

Subscribe to this mod's changes

sipcode CLAUDE.md is an instructions file published in the GitHub repository Anuj7411/sipcode (46 stars, last pushed 1mo ago), licensed MIT. It adds 362 tokens to every session, about $0.0018 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 2026-08-30.

ai-codinganthropicastclaude-codeclaude-desktopcli
Related

Other instructions, from other repositories

jcodemunch-mcp CLAUDE.md

Claude Code instructions for jgravelle/jcodemunch-mcp, covering jcodemunch-mcp — project brief, current state, key files, cli subcommands and architecture notes.

jgravelle/jcodemunch-mcp · 34,089 tokens

jcodemunch-mcp AGENTS.md

AGENTS.md instructions for jgravelle/jcodemunch-mcp, covering code exploration policy, session-aware routing and model-driven tool tiering.

jgravelle/jcodemunch-mcp · 1,312 tokens

codemap AGENTS.md

Instructions for stainless-code/codemap, a project described as: Cut AI-agent token waste 90% — query a local SQLite structural index of your JS/TS/CSS codebase with SQL in one round-trip instead of 3–5 file reads. Symbols, imports, calls, components, CSS tokens, coverage, markers. CLI, MCP (21 tools), HTTP, GitHub…

stainless-code/codemap · 632 tokens

token-pilot CLAUDE.md

Claude Code instructions for Digital-Threads/token-pilot, covering project instructions for ai agents, beads issue tracker, quick reference, rules and session completion.

Digital-Threads/token-pilot · 920 tokens

mcp-server-tree-sitter AGENTS.md

Instructions for wrale/mcp-server-tree-sitter, covering agents.md, project overview, setup, before committing and key architecture.

wrale/mcp-server-tree-sitter · 823 tokens

codexray CLAUDE.md

Instructions for NeuralRays/codexray, covering codexray — ai agent instructions, workflow and key principle.

NeuralRays/codexray · 324 tokens