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/roccodaffuso/sift/claude-mdgit clone --depth 1 https://github.com/roccodaffuso/siftWrote 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/roccodaffuso/sift/claude-md)<a href="https://agentmods.dev/instructions/roccodaffuso/sift/claude-md"><img src="https://agentmods.dev/badge/instructions/roccodaffuso/sift/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 | $0.00285 | $0.00285 |
| Opus 5 | $0.00143 | $0.00143 |
| Sonnet 5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
sift 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 4d 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.
What it actually says
Claude Code Project Notes
This repository includes a portable Agent Skill for local session-memory search:
.agents/skills/sift-memory/SKILL.md
Use it when prior Claude Code, Codex, Cursor, or OpenCode chat/session history could help answer a question, recover a decision, debug a regression, or continue project work.
Core commands:
sift index --json
sift "<query>" --limit 10 --json
sift "<query>" --tool claude --limit 10 --json
sift "<query>" --tool codex --limit 10 --json
sift "<query>" --tool cursor --limit 10 --json
sift "<query>" --tool opencode --limit 10 --json
sift show "<ref>" --json
sift list --limit 10 --json
When the global command is unavailable inside this repo, use node ./bin/sift.js with the same arguments.
Privacy constraints:
- Keep all
siftusage local. - Do not send log contents or index data to remote services.
- Do not write to Claude Code, Codex, Cursor, or OpenCode source logs/databases.
- Follow only relevant result refs with
sift showwhen surrounding context is needed. - Summarize only relevant findings; do not paste large raw logs.
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.
- 4d ago First seen · 33 lines · 285 tokens per session scan A 0d80622fe1a3
sift CLAUDE.md is an instructions file published in the GitHub repository roccodaffuso/sift (2 stars, last pushed 1mo ago), licensed MIT. It adds 285 tokens to every session, about $0.0014 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
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.
data-scientist copilot-instructions.md
Instructions for realnghon/data-scientist, covering github copilot — 项目指令：data scientist 工作流 and 共享核心 — 回答前请阅读.