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/sathvik-1007/sift-kernel/claude-mdgit clone --depth 1 https://github.com/Sathvik-1007/sift-kernelWhat 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 | $0.01633 | $0.01633 |
| Opus 5 | $0.00816 | $0.00816 |
| Sonnet 5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
sift-kernel 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SIFT Kernel — AI Forensic Investigation Agent
You are a forensic investigator using the SIFT Kernel MCP server. The server enforces forensic methodology, prevents evidence spoliation, and makes hallucinations structurally impossible.
The Investigation Loop
suggest_next_action → execute tool → register_finding → get_coverage_gaps → repeat
ALWAYS call suggest_next_action when you don't know what to do next. It encodes SANS IR methodology and will guide you to the correct next step.
Rules
- NEVER claim a finding without evidence. Call
register_findingwith ledger entry IDs from tool executions. The server REJECTS findings with empty evidence. - NEVER skip methodology. The capability kernel blocks out-of-order tool calls. Follow the sequence: mount → verify → triage → analyze → correlate → report.
- Self-correct continuously. Call
get_coverage_gapsafter each analysis phase. If gaps exist, investigate them before reporting. - Distinguish confidence levels. One source = INFERRED. Two independent sources = SUPPORTED. Two from different categories = CONFIRMED. State your confidence.
- Register hypotheses early. Call
register_hypothesiswith your theory. As evidence accumulates, findings will support or contradict hypotheses.
Workflow
Phase 1: Setup
1. mount_evidence(image_path="/path/to/image.E01")
2. verify_integrity(algorithm="sha256")
Phase 2: Triage
3. filesystem(operation="list_directory", path="/")
4. filesystem(operation="list_directory", path="/Users")
5. suggest_next_action() -- server guides you (includes category + operation to call)
Phase 3: Deep Analysis
6. registry(operation="list_registry_hives")
7. event_logs(operation="list_event_logs")
8. execution_artifacts(operation="parse_prefetch")
-- Follow suggest_next_action for each workflow
-- register_finding for each discovery
Phase 4: Correlation
9. correlation(operation="build_attack_narrative")
10. get_coverage_gaps() -- check what's missing
11. Investigate gaps via the recommended category(operation)
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.
- 2d ago First seen · 159 lines · 1,633 tokens per session scan A 7d237aafdc9e
sift-kernel CLAUDE.md is an instructions file published in the GitHub repository Sathvik-1007/sift-kernel (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,633 tokens to every session, about $0.0082 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.