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/dzmitrys-dev/supamem/claude-mdgit clone --depth 1 https://github.com/dzmitrys-dev/supamemWrote 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/dzmitrys-dev/supamem/claude-md)<a href="https://agentmods.dev/instructions/dzmitrys-dev/supamem/claude-md"><img src="https://agentmods.dev/badge/instructions/dzmitrys-dev/supamem/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 | $0.00986 | $0.00986 |
| Opus 5 | $0.00493 | $0.00493 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
supamem 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — supamem
Claude Code instructions for the supamem repository.
@AGENTS.md
Workflow
- Use
/brainstormbefore ambiguous feature work - Use
/write-planbefore multi-step implementation - Use
/systematic-debugbefore proposing bug fixes - Verify with
uv run pytest(project root) anduv run ruff check src testsbefore claiming done
Dual-Memory Tool Use (HARD — eat your own dog food)
This repo SHIPS supamem. If you don't call its MCP tools yourself, end users won't either. Before any of the following, your FIRST action MUST be a mcp__supamem__dual_memory_search (or mcp__supamem__qdrant_find for semantic-only):
- ANY edit under
src/supamem/— search first, edit second. No exceptions. - Touching retrieval / embedder / chunker / indexer / hooks / installer code
- Investigating a non-obvious bug, test failure, or surprising behavior
- Architecture decisions, ADR-shaped questions ("should I rename X?", "where does Y belong?")
- Before proposing CONTEXT.md decisions during
/gsd-discuss-phase
Anti-patterns:
- Searching AFTER editing (the point is to load context BEFORE choosing an approach)
- Skipping because "I already know" — that mindset is exactly what wastes end-user tokens
- Calling only the structural side when the question is "why" — semantic memory has the rationale
If the search returns nothing relevant, say so explicitly ("supamem search empty — proceeding from code") so the gap is visible. Drift between this rule and actual behavior is the bug we're trying to fix in v0.2.0.
Hard Constraints
- NEVER use bare
print()— import fromsrc/supamem/console.py - NEVER print to stdout from
mcp_server.py— JSON-RPC purity (useerr_console) - NEVER hardcode collection names — read
config.collection - NEVER skip the PEP 639 license check on release —
license = "MIT"SPDX, noLicense ::classifier - NEVER force-move a published git tag — PyPI rejects re-uploads of the same version
- NEVER suppress errors in indexing/retrieval paths — surface via
err_console - Update-check is the ONLY code path where blanket
except Exception: passis acceptable - NEVER edit
README.mdwithout also updating the 4 translations (README.zh-CN.md,README.es.md,README.ja.md,README.ru.md) AND bumping thesynced-withSHA marker on line 2 of each. See AGENTS.md → "README Translations" for the one-liner. - ALWAYS update
llms.txtwhen CLI subcommands, MCP tools, env vars, version, or major doc structure changes. Drift between code andllms.txtis a documentation bug — see AGENTS.md → "llms.txt is MANDATORY". - NEVER commit GSD planning artifacts (
.planning/,.gsd/,.continue-here.md,HANDOFF-*.md) to the supamem repo — they are gitignored and meant to stay local. supamem ships as a clean Python package, not a planning workspace. Usedocs/adr/,CHANGELOG.md, or commit messages for durable public design records.
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 · 64 lines · 986 tokens per session scan A 2fc8addffa00
supamem CLAUDE.md is an instructions file published in the GitHub repository dzmitrys-dev/supamem (12 stars, last pushed 13d ago), licensed MIT. It adds 986 tokens to every session, about $0.0049 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
obsidianos_work AGENTS.md
Instructions for benoror/obsidianos_work, covering agents, skills, skill proxies (symlinks to .agents/skills/), rules and agent wrappers.
toon-memory AGENTS.md
Instructions for LuiggiVal08/toon-memory, covering agents.md, build & verify, architecture, smarter memory pattern and visual memory pattern.
skill-memory AGENTS.md
AGENTS.md instructions for memodb-io/skill-memory, a project described as: agent skill as memory layer.
repo-context-mcp AGENTS.md
Instructions for nduc99911/repo-context-mcp, covering agents.md — repo-context-mcp, project, layout, commands and conventions.
EGC copilot-instructions.md
Copilot instructions for Fmarzochi/EGC, covering copilot instructions for egc, repository conventions, readme and translations, code review priorities and egc project memory.
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.