Borrowing it
Nothing to install: this file belongs to ashlesh-t/cognirepo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ashlesh-t/cognirepo/main/CLAUDE.mdgit clone --depth 1 https://github.com/ashlesh-t/cognirepoWrote 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/ashlesh-t/cognirepo/claude-md)<a href="https://agentmods.dev/instructions/ashlesh-t/cognirepo/claude-md"><img src="https://agentmods.dev/badge/instructions/ashlesh-t/cognirepo/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.
<a href="https://agentmods.dev/instructions/ashlesh-t/cognirepo/claude-md"><img src="https://agentmods.dev/badge/instructions/ashlesh-t/cognirepo/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02241 | $0.02241 |
| Opus 5 | $0.01120 | $0.01120 |
| Sonnet 5 | $0.00448 | $0.00448 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade A, and why
cognirepo 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 12d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
CogniRepo — local cognitive infrastructure layer for AI agents. Semantic memory (FAISS) + knowledge graph + AST index + MCP server. Goal: cut token overhead and context loss between AI sessions, not add complexity.
Key rules
- All storage lives under
.cognirepo/in the project root, with these exceptions: cross-agent handoff snapshots are written to~/.cognirepo/<repo>/last_context.jsonso multiple agent processes (Claude, Gemini, Cursor) can share context across sessions; the org-level dependency graph lives at~/.cognirepo/org_graph.pklfor the same reason; and generated human-facing reports (currentlycognirepo insights) are written to.claude/insights/<repoName>-insights.htmlin the project root — these are presentation artifacts for the human + their agent tooling, not machine state, so keeping them out of.cognirepo/avoids polluting index/memory storage, and.claude/is already the agent-facing, gitignored surface. The machine-readable twin remains under.cognirepo/docs/. - Org graph model: main repo = hub/parent. Sub-repos/microservices are registered as children via
cognirepo init --parent-repo <path>. Edges are IMPORTS/CALLS_API/SHARES_SCHEMA/CHILD_OF/DISCOVERED. AI agents add DISCOVERED edges dynamically vialink_repos(). Children can be interconnected. - Model names only in
intelligence/orchestrator/classifier.py. No hardcoding elsewhere. intelligence/retrieval/hybrid.pyowns all retrieval. Never call FAISS or the graph directly from tools.- Tools in
interface/tools/are the single entry point. Stateless, no cross-tool calls. - When ever any code parts get updated and if the document existing ones dont cover or needs changes ,then update the docs accordingly.
Session start sequence (run in this order)
get_session_brief()— architecture + hot symbols + index healthget_last_context()— what the last agent was looking atget_user_profile()— user's interaction style; applyframing_hintsto ALL responsesget_error_patterns()— past recurring errors; avoid repeating them
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.
- 12d ago First seen · 142 lines · 2,241 tokens per session scan A f96e5b001760
cognirepo CLAUDE.md is an instructions file published in the GitHub repository ashlesh-t/cognirepo (14 stars, last pushed 8d ago), licensed MIT. It adds 2,241 tokens to every session, about $0.0112 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
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).