Borrowing it
Nothing to install: this file belongs to hermes-labs-ai/forgetted. 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/hermes-labs-ai/forgetted/main/CLAUDE.mdgit clone --depth 1 https://github.com/hermes-labs-ai/forgettedWrote 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/hermes-labs-ai/forgetted/claude-md)<a href="https://agentmods.dev/instructions/hermes-labs-ai/forgetted/claude-md"><img src="https://agentmods.dev/badge/instructions/hermes-labs-ai/forgetted/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 5.1 | $0.00600 | $0.00600 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
forgetted 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 8d 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 — Agent Instructions for forgetted
What this project is
forgetted is a Python package that gives AI agents selective memory governance.
It blocks writes to persistence layers during a "forgetted window" while keeping
reads working normally. The agent has full context but can't write new context.
Architecture
forgetted/
├── __init__.py # Package exports, version
├── trigger.py # Detect forgetted activation in user messages
├── guard.py # ForgetGuard — builtins.open monkey-patch
├── checkpoint.py # Save/load resumption files
├── cleaner.py # Find and delete session logs
├── session.py # ForgetSession — orchestrator (main entry point)
└── adapters/
├── base.py # PersistenceAdapter ABC
├── file_write.py # Wraps ForgetGuard as adapter
└── mem0.py # mem0 semantic memory adapter
Key design decisions
- builtins.open patch is the safety net — catches writes from any layer
- Adapter pattern for extensibility — each persistence layer registers separately
- No-op returns instead of raising — agent code doesn't crash, writes silently vanish
- ForgetSession.stop() ordering: enable first → cleanup → delete log (so cleanup code can write)
- Idempotent — double-start, stop-before-start, double-stop are all safe no-ops
Running tests
pip install -e ".[dev]"
pytest tests/ -v
99 tests + 2 xfail. Test files:
test_forgetted.py— core module tests (triggers, guard, checkpoint, cleaner)test_session.py— ForgetSession orchestrator teststest_adapters.py— FileWriteAdapter and Mem0Adapter teststest_adversarial.py— bypass vectors, false positives, edge cases
Known limitations (documented as xfail tests)
Path.write_text()/Path.write_bytes()bypass builtins.open (uses os.open internally)os.open()+os.write()bypass (low-level file descriptors)subprocess/ shell commands bypass (outside Python)rename()into protected paths bypass (filesystem operation)- Nested ForgetSessions break (inner stop restores original open)
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.
- 8d ago First seen · 64 lines · 600 tokens per session scan A 925329bd5ea5
forgetted CLAUDE.md is an instructions file published in the GitHub repository hermes-labs-ai/forgetted (2 stars, last pushed 28d ago), licensed Apache-2.0. It adds 600 tokens to every session, about $0.0030 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 2026-08-31.
Other instructions, from other repositories
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).
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).
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.
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.