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/julymetodiev/post-cortex/claude-mdgit clone --depth 1 https://github.com/julymetodiev/post-cortexWrote 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/julymetodiev/post-cortex/claude-md)<a href="https://agentmods.dev/instructions/julymetodiev/post-cortex/claude-md"><img src="https://agentmods.dev/badge/instructions/julymetodiev/post-cortex/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 | $0.00809 | $0.00809 |
| Opus 5 | $0.00404 | $0.00404 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
post-cortex 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 5d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Docs: PROJECT.md | No "Co-Authored-By" in commits
Session
Session ID bf52f62e-8e26-4e9e-8501-c42753d9a9ee
Workspace ID | ba76f569-a50d-46cd-a5dd-7c5577f12d1f
Rules
- Search before answering — call
semantic_search(session → workspace → global) BEFORE answering any code/architecture question - Log after discovery — call
update_conversation_contextAFTER making decisions, fixing bugs, or changing code - Self-check — enforced by Stop hook automatically
Interaction Types
qa · decision_made · problem_solved · code_change · requirement_added · concept_defined
MCP Tools
Call directly — do NOT use subagents for simple search/log operations.
| Tool | When |
|---|---|
semantic_search |
Before answering code/arch questions. Scope: session / workspace / global. Returns structured payload (scores, content_id, content_type, snippet, timestamp) |
update_conversation_context |
After decisions, fixes, changes. Single or bulk. entities (≥1) and relations (≥1) are required (dangling/self-relations rejected). Content: typed keys (decision/rationale, problem/solution, concept/definition, question/answer, file/changes, requirement) or generic title/description |
get_structured_summary |
Session analysis and reviews. include values: decisions, insights, entities, questions, all. Also: decisions_limit, entities_limit, questions_limit, concepts_limit, min_confidence, compact |
query_conversation_context |
Flexible queries. query_type values: find_related_entities, get_entity_context, search_updates, entity_importance, entity_network, find_related_content (topic, max_results), key_decisions, key_insights (limit), session_statistics, structured_summary, decisions, open_questions, assemble_context, trace_relationships, get_most_important_entities, find_entities_by_type |
session |
Sessions: create, list, load (session_id), search (query), update_metadata (session_id + name/description; preserves created_at), delete (evicts cache + storage) |
manage_workspace |
Workspace CRUD: create, list, get, delete, add_session, remove_session |
assemble_context |
Graph-aware retrieval (semantic + 1-hop traversal + impact analysis = reverse dependencies, "who depends on X"). Scope: session or workspace. Returns items (budget-packed), entity_context (with DirectMention / GraphNeighbor{via,relation}), impact, total_tokens, formatted_text (LLM-ready) |
manage_entity |
delete (entity_name; cascades typed edges), delete_update (entry_id; removes a single context row from hot/warm/incremental caches and persists) |
admin |
health, vectorize_session (session_id), vectorize_stats, create_checkpoint (session_id) |
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.
- 5d ago First seen · 43 lines · 809 tokens per session scan A 2e7651b3760e
post-cortex CLAUDE.md is an instructions file published in the GitHub repository julymetodiev/post-cortex (20 stars, last pushed 3mo ago), licensed MIT. It adds 809 tokens to every session, about $0.0040 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.
Other instructions, from other repositories
long-term-memory CLAUDE.md
Claude Code instructions for ihwooMil/long-term-memory, covering long-term memory system and conventions.
llm-wiki-agent CLAUDE.md
Claude Code instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, slash commands (claude code), directory layout, page format and ingest workflow.
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
memora CLAUDE.md
Claude Code instructions for agentic-box/memora, covering memora and memory.
braindb CLAUDE.md
Claude Code instructions for dimknaf/braindb, covering braindb — claude instructions, ⚠ tool priority — read this first, it overrides habit, at the start of every session, 1. get always-on rules (behavioral guidelines) and project structure.
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.