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/mythographica/strategy/agents-mdgit clone --depth 1 https://github.com/mythographica/strategyWrote 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/mythographica/strategy/agents-md)<a href="https://agentmods.dev/instructions/mythographica/strategy/agents-md"><img src="https://agentmods.dev/badge/instructions/mythographica/strategy/agents-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 | $0.04110 | $0.04110 |
| Opus 5 | $0.02055 | $0.02055 |
| Sonnet 5 | $0.00822 | $0.00822 |
| Haiku 4.5 | $0.00411 | $0.00411 |
Grade A, and why
strategy AGENTS.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 today.
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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - @mnemonica/strategy
Guidance for AI agents working on the Mnemonica Strategy MCP Server.
What this is
@mnemonica/strategy is the live bridge between a running Mnemonica
runtime and the tools around it — the center of the topology star: agents
drive it over MCP; applications self-host its channel; visualization
tooling (Mnemographica) connects as a monitoring client. It attaches to a
target Node.js process via the Chrome Debug Protocol (CDP) — zero
instrumentation of the target — then moves construction traffic onto a
WebSocket channel injected into that process. Apps that may instrument
themselves can skip CDP entirely: see The app-side client module
below. The long-term UX goal (errored trace → one click → debugger
reproduction on real data) lives in docs/northstar.md.
The development-mode side of the same channel (defining and swapping
constructors in a live app, no restart) is documented in
docs/live-craft.md.
The 3-tool surface (do not expand without discussion)
The server exposes exactly 3 MCP tools (src/server.ts):
- execute —
{ context, command, message }runs a command file. - list —
{ context? }lists commands, grouped by context and folder. - help —
{ context, command }returns metadata, schema, examples.
Arguments travel as a JSON string in message; every command parses
args.message first. This 3-tool design is deliberate and liked — do not
propose adding tools lightly.
Execution model — the truth table
| Where code runs | How |
|---|---|
| Strategy MCP process (local) | executeCommand in src/server.ts runs EVERY command file locally: module.exports.run files via require(), all others via new Function('ctx', body). There is no remote eval of command files. |
| Target runtime (remote) | Only code passed to Runtime.evaluate() over CDP runs in the target: (a) CDPConnection.evaluate() / getMnemonicaTypes(), (b) cdp-scripts/*.js payloads that RPC wrapper commands read from disk and send. |
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.
- today Changed · +52 lines · +815 tokens per session 45ab696e3296
- 3d ago First seen · 271 lines · 3,295 tokens per session scan A 46e278bf34b0
strategy AGENTS.md is an instructions file published in the GitHub repository mythographica/strategy (0 stars, last pushed today), licensed MIT. It adds 4,110 tokens to every session, about $0.0205 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 2026-09-01.
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.