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/nickcirv/engram/claude-mdgit clone --depth 1 https://github.com/NickCirv/engramWrote 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/nickcirv/engram/claude-md)<a href="https://agentmods.dev/instructions/nickcirv/engram/claude-md"><img src="https://agentmods.dev/badge/instructions/nickcirv/engram/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 | $0.00947 | $0.00947 |
| Opus 5 | $0.00474 | $0.00474 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
engram 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- engram CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Structure (auto-generated by engram)
Graph: 451 nodes, 1005 edges | 96% extracted, 4% inferred View: general
Core entities
extractDirectory()(function, 2 connections) — src/miners/ast-miner.tsextractFile()(function, 2 connections) — src/miners/ast-miner.tsgenerateSummary()(function, 2 connections) — src/autogen.tswriteToFile()(function, 2 connections) — src/autogen.tsparseReadLikeBashCommand()(function, 2 connections) — src/intercept/handlers/bash.tscreateAuthService()(function, 2 connections) — tests/intercept/handlers/bash.test.tshashPassword()(function, 2 connections) — tests/intercept/handlers/bash.test.tsSessionStore(class, 2 connections) — tests/intercept/handlers/bash.test.ts
Structure
./— tsup.config.tsbench/— runner.tssrc/— autogen.ts, cli.ts, core.ts, dashboard.ts, hooks.ts, serve.ts, watcher.tssrc/ccs/— exporter.ts, importer.tssrc/db/— migrate.tssrc/generators/— aider-context.ts, cursor-mdc.tssrc/graph/— path-utils.ts, query.ts, render-utils.ts, schema.ts, store.tssrc/intelligence/— hook-log.ts, token-tracker.tssrc/intercept/— component-status.ts, context.ts, cursor-adapter.ts, dispatch.ts, formatter.ts, installer.ts, memory-md.ts, safety.ts, stats.tssrc/intercept/handlers/— bash.ts, cwd-changed.ts, edit-write.ts, lsp-capture.ts, post-tool.ts, pre-compact.ts, read.ts, session-start.ts, user-prompt.tssrc/miners/— ast-miner.ts, git-miner.ts, session-miner.ts, skills-miner.tssrc/providers/— ast.ts, context7.ts, engram-git.ts, engram-mistakes.ts, engram-structure.ts, grammar-loader.ts, lsp-connection.ts, lsp.ts, mempalace.ts, obsidian.ts, resolver.ts, types.tssrc/server/— http.tssrc/tuner/— config.ts, index.tssrc/types/— sql.js.d.tstests/— ast-miner.test.ts, autogen.test.ts, core.test.ts, mistake-memory.test.ts, provider-cache.test.ts, render-utils.test.ts, skills-miner.test.ts, store.test.ts, stress.test.ts, watcher.test.tstests/ccs/— ccs.test.tstests/db/— migrate.test.tstests/fixtures/— sample.tstests/generators/— cursor-mdc.test.tstests/intercept/— cli-intercept.test.ts, context.test.ts, cursor-adapter.test.ts, dispatch-new-events.test.ts, dispatch.test.ts, formatter.test.ts, get-file-context.test.ts, hook-log.test.ts, installer.test.ts, memory-md.test.ts, mistakes-filter.test.ts, render-file-structure.test.ts, safety.test.ts, spike-regression.test.ts, stats.test.tstests/intercept/handlers/— bash.test.ts, cwd-changed.test.ts, edit-write.test.ts, post-tool.test.ts, pre-compact.test.ts, read.test.ts, session-start.test.ts, user-prompt.test.tstests/providers/— ast.test.ts, lsp.test.ts, resolver.test.tstests/server/— http.test.tstests/tuner/— tuner.test.ts
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 · 58 lines · 947 tokens per session scan A 914eb68d80f3
engram CLAUDE.md is an instructions file published in the GitHub repository NickCirv/engram (141 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 947 tokens to every session, about $0.0047 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
Dragon-Brain CLAUDE.md
Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.
ChatCrystal AGENTS.md
AGENTS.md instructions for ZengLiangYi/ChatCrystal, covering agents.md, project overview, commands, development (server port 3721 + client port 13721) and build for production.
superlocalmemory AGENTS.md
AGENTS.md instructions for qualixar/superlocalmemory, covering gitnexus — code intelligence, always do, never do, resources and cli.
superlocalmemory copilot-instructions.md
Copilot instructions for qualixar/superlocalmemory, covering superlocalmemory (slm) — agent rules, session start, remember, recall and optimize (fail-open).
forensic-deepdive CLAUDE.md
Instructions for Dhevenddra/forensic-deepdive, covering claude.md — forensic-deepdive, what this project is, stack, critical commands and session start protocol (mandatory).
forensic-deepdive AGENTS.md
Instructions for Dhevenddra/forensic-deepdive, covering agents.md, cross-edit obligation, mandatory reading order at session start and mandatory action at session end.