Lossless Claw is an OpenClaw plugin that preserves complete conversation history while keeping the active context within an AI model’s token limit. It stores messages in SQLite and builds linked summaries that agents can search and expand, with the catalogue providing skills and an instruction for its workflow.
Borrowing it
Nothing to install: this file belongs to Martian-Engineering/lossless-claw. 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/Martian-Engineering/lossless-claw/main/AGENTS.mdgit clone --depth 1 https://github.com/Martian-Engineering/lossless-clawWrote 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/martian-engineering/lossless-claw/agents-md)<a href="https://agentmods.dev/instructions/martian-engineering/lossless-claw/agents-md"><img src="https://agentmods.dev/badge/instructions/martian-engineering/lossless-claw/agents-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/martian-engineering/lossless-claw/agents-md"><img src="https://agentmods.dev/badge/instructions/martian-engineering/lossless-claw/agents-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 | $0.00909 | $0.00909 |
| Opus 5.5 | $0.00364 | $0.00364 |
| Sonnet 5.5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
lossless-claw 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 1mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions
Principles
- Lossless means lossless. Do not delete, purge, truncate, or otherwise discard persisted user data unless the user has explicitly invoked a command or approved an action whose purpose is to remove that data.
- Automatic maintenance, bootstrap, repair, migration, compaction, cleanup, or rotation code must preserve user data. If continuity is uncertain, prefer degraded coverage, stale markers, warnings, or follow-up repair work over destructive recovery.
- Backups are not a substitute for this rule. The live system must not rely on being able to restore user data after an automatic delete.
PR Review And Merge
- Before merging a PR, check whether it changes user-facing behavior or should appear in npm release notes.
- If yes, make sure a maintainer adds a
.changeset/*.mdfile before merge or immediately after in a follow-up PR. - Do not expect external contributors to know or run the Changesets workflow.
- Use the smallest appropriate bump:
patch: fixes, compatibility work, docs-visible behavior changesminor: new features or notable new behaviormajor: breaking changes
- Treat a PR as not release-ready until the changeset question has been answered.
Release Notes Source Of Truth
- Follow RELEASING.md for the repo's full Changesets and publish workflow.
OpenClaw Host Compatibility
- When a change introduces or depends on a newer OpenClaw plugin API, runtime capability, config policy, manifest field, command behavior, or host integration contract, verify the first stable OpenClaw release that supports it before coding or publishing. Distinguish beta tags from stable releases.
- Update every compatibility declaration in the same change:
package.jsonpeerDependencies.openclawpackage.jsonopenclaw.compat.pluginApipackage.jsonopenclaw.compat.minGatewayVersionpackage.jsonopenclaw.compat.testedpackage.jsonopenclaw.build.openclawVersionpackage-lock.json
- Do not add an OpenClaw upper bound such as
<2026.x.0unless a specific known incompatibility requires it. - Preserve
peerDependenciesMeta.openclaw.optionalwhen it exists; tightening the supported host version does not mean the package must install OpenClaw directly. - Refresh
package-lock.jsonwithnpm install --package-lock-onlyafter changing OpenClaw peer or compatibility metadata, then verifynpm ci --package-lock-only --ignore-scriptsso CI will not fail on stale lock metadata. - Add or update a regression test that asserts the required OpenClaw version metadata and, when relevant, the runtime capability gate or error path.
- Update user-facing documentation in the same change. At minimum, document the minimum OpenClaw version, why it is required, and the fallback path for users who cannot upgrade yet.
- Add a Changeset for any package compatibility change. Use
patchfor compatibility metadata fixes unless the change is breaking for currently supported users in a way that warrants a larger bump.
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.
- 1mo ago First seen · 48 lines · 909 tokens per session scan A ff88d476af1c
lossless-claw AGENTS.md is an instructions file published in the GitHub repository Martian-Engineering/lossless-claw (4,911 stars, last pushed today), licensed MIT. It adds 909 tokens to every session, about $0.0036 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.