Agent skill

Slm Compress

by qualixar in qualixar/superlocalmemory

AGPL-3.0Auto-check: notesAgent Workflows

Install Slm Compress

skills CLI

$ npx skills add qualixar/superlocalmemory --skill slm-compress -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install qualixar/superlocalmemory slm-compress --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/qualixar/superlocalmemory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/slm-compress .claude/skills/slm-compress && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "slm-compress" agent skill from https://github.com/qualixar/superlocalmemory/tree/main/plugin/skills/slm-compress into .claude/skills/slm-compress/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slm-compress", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/qualixar/superlocalmemory/tree/main/plugin/skills/slm-compress

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add qualixar/superlocalmemory --skill slm-compress -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install qualixar/superlocalmemory slm-compress --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/qualixar/superlocalmemory.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/slm-compress .agents/skills/slm-compress && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "slm-compress" agent skill from https://github.com/qualixar/superlocalmemory/tree/main/plugin/skills/slm-compress into .agents/skills/slm-compress/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slm-compress", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add qualixar/superlocalmemory --skill slm-compress -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install qualixar/superlocalmemory slm-compress --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/qualixar/superlocalmemory.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/slm-compress .cursor/skills/slm-compress && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "slm-compress" agent skill from https://github.com/qualixar/superlocalmemory/tree/main/plugin/skills/slm-compress into .cursor/skills/slm-compress/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slm-compress", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/qualixar/superlocalmemory.git --path plugin/skills/slm-compress

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add qualixar/superlocalmemory --skill slm-compress -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install qualixar/superlocalmemory slm-compress --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/qualixar/superlocalmemory.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/slm-compress .gemini/skills/slm-compress && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "slm-compress" agent skill from https://github.com/qualixar/superlocalmemory/tree/main/plugin/skills/slm-compress into .gemini/skills/slm-compress/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slm-compress", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install qualixar/superlocalmemory slm-compress

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add qualixar/superlocalmemory --skill slm-compress -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/qualixar/superlocalmemory.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/slm-compress .github/skills/slm-compress && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "slm-compress" agent skill from https://github.com/qualixar/superlocalmemory/tree/main/plugin/skills/slm-compress into .github/skills/slm-compress/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slm-compress", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add qualixar/superlocalmemory --skill slm-compress -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install qualixar/superlocalmemory slm-compress --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/qualixar/superlocalmemory.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/slm-compress .opencode/skills/slm-compress && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "slm-compress" agent skill from https://github.com/qualixar/superlocalmemory/tree/main/plugin/skills/slm-compress into .opencode/skills/slm-compress/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slm-compress", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: slm-compress
GitHub stars: 231
Token cost: ~1.6k tokens
SKILL.md length: 574 words
Files: 1
Skills in repo: 17
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Tasks that involve Context engineering
SKILL.md covers Purpose, Primary MCP Tool: slm_compress, Recovery Tool: slm_retrieve and Decision: When to Compress, plus 5 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Slm Compress is an agent skill from qualixar/superlocalmemory. Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slmcompress(content, mode, reversible, ttlseconds) to shrink content; if the result is lossy a ccrid is returned so you can call slmretrieve(ccrid) later to recover the exact original; always fail-open (ok:false → continue with the original).

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Context engineering. The repository describes itself as: Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253. The licence is AGPL-3.0.

When your agent uses it

Tasks that involve Context engineering

Example prompts

“/slm-compress”

Requirements

Python 3
Pre-approved tools (allowed-tools): slm_compress, slm_retrieve, Bash

What it can do on your machine

Read from SKILL.md and the folder at commit 26f8c68. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- slm_compress
- slm_retrieve
- Bash
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json, python and bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Slm Compress loads about 1.6k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 574 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~97
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
```
allowed-tools: slm_compress, slm_retrieve, Bash
```

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from qualixar/superlocalmemory at commit 26f8c68, republished under its AGPL-3.0 licence (© qualixar). 574 words, ~1,562 tokens.

Download SKILL.mdSave it as .claude/skills/slm-compress/SKILL.md (or your agent's skills folder).

name: slm-compress
description: Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slm_compress(content, mode, reversible, ttl_seconds) to shrink content; if the result is lossy a ccr_id is returned so you can call slm_retrieve(ccr_id) later to recover the exact original; always fail-open (ok:false → continue with the original).
allowed-tools: slm_compress, slm_retrieve, Bash
when_to_use: compress context, shrink output, save tokens, context window full, long transcript, compress tool result, reduce tokens, large output, compress text

slm-compress — Reversible Context Compression (Surface B)

Purpose

When a tool output, transcript, or accumulated context grows large enough to crowd out working space, slm_compress reduces it in-place. The compressed form is used for the remainder of the session; the exact original is recoverable on demand via slm_retrieve. This works without a proxy and without touching ANTHROPIC_BASE_URL, so the full 1M context window is never sacrificed.

Primary MCP Tool: slm_compress

slm_compress(
    content:      str,          # required — text to compress (max 1 MB)
    mode:         str = "auto",  # "normalize" | "auto" | "aggressive"
    reversible:   bool = True,  # store original in CCR for later retrieval
    ttl_seconds:  int = 86400,  # CCR lifetime in seconds (default 24 h)
) -> dict

Return dict (all keys always present)

Key	Type	Meaning
`ok`	bool	`True` on success; `False` on internal error or empty input
`compressed`	str	Compressed text (or original on failure)
`strategy`	str	Which strategy was applied (e.g. `"normalize"`, `"none"`)
`tokens_before`	int	Word-count estimate of the input
`tokens_after`	int	Word-count estimate of the output
`ratio`	float	`tokens_after / tokens_before` (lower = more compact)
`lossy`	bool	Whether information was removed
`ccr_id`	str \| None	UUID4 session token; present only when `lossy=True` and `reversible=True`
`note`	str \| None	Human-readable note (e.g. warnings, recovery hint)

Mode semantics (verified from source)

"normalize" — lossless whitespace collapse; no daemon dependency; lossy: false, ccr_id: null.
"auto" — delegates to CompressRouter; may be lossy depending on daemon config; default.
"aggressive" — requests aggressive compression from the daemon; daemon must have compress_mode=aggressive set in config; note field will warn if daemon config does not match.

Recovery Tool: slm_retrieve

When slm_compress returns lossy: true, the original is stored under the ccr_id. Use slm_retrieve to get it back:

slm_retrieve(ccr_id: str) -> dict

Key	Type	Meaning
`ok`	bool	`True` when content was found
`content`	str \| None	Original text, decoded from UTF-8 (or Latin-1 fallback)
`size_bytes`	int	Byte length of the stored original
`error`	str \| None	Error message on failure; `None` on success

ccr_id must be a valid UUID4. Non-UUID4 strings return ok: false immediately.

CCR security rule

ccr_id values are unguessable session tokens, and the stored original can be read back only by the same agent (or, for a remote caller, the same access key) that compressed it. Treat them like short-lived credentials:

Never log them.
Never share them across agents.
Never pass them as tool arguments to any tool other than slm_retrieve.
Never compress a ccr_id string itself.
They expire after ttl_seconds (default 24 h); slm_retrieve returns ok: false after expiry.

Show full SKILL.md (217 more words)Show less

Decision: When to Compress

Compress when:

A single tool output or transcript exceeds approximately 2 000 characters.
You are accumulating repeated context (e.g. full file reads across multiple steps).
Context is nearing the point where recall quality or response quality degrades.

Do NOT compress:

Code you are about to read, edit, or diff — you need every character.
JSON you will parse programmatically — compression may alter structure.
Secrets, credentials, or ccr_id strings.
Anything under ~500 characters — overhead exceeds benefit.
The compressed form of content already compressed this session.

Fail-Open Guarantee

slm_compress never raises an exception. On any internal error it returns:

json

{ "ok": false, "compressed": "<original input>", "ratio": 1.0, ... }

When ok is false, continue with the original content. Never block a task waiting for compression to succeed.

Worked Example

python

# Step 1: compress a large tool output
result = await slm_compress(
    content=long_log_text,
    mode="auto",
    reversible=True,
    ttl_seconds=3600,
)

if result["ok"]:
    working_text = result["compressed"]
    ccr_id = result["ccr_id"]   # None if lossless
else:
    working_text = long_log_text  # fail-open
    ccr_id = None

# ... work with working_text ...

# Step 2: restore original when needed (e.g. before final summary)
if ccr_id:
    restore = await slm_retrieve(ccr_id=ccr_id)
    if restore["ok"]:
        original_text = restore["content"]

Secondary CLI (fallback when MCP is unavailable)

Prefer the MCP tools above. If you must use the command line:

bash

slm compress status [--json]
slm compress mode safe|aggressive [--json]
slm compress code on|off [--json]
slm compress prose on|off [--json]
slm compress ccr on|off [--json]
slm compress align on|off [--json]

These subcommands control daemon-level compression settings — they do not compress content inline. For inline compression, use slm_compress via MCP.

Size Cap

Content over 1 MB (1 000 000 bytes UTF-8) is processed but reversible is forced to False and ccr_id will be None. The note field will state "content over 1MB: ccr skipped".

slm-cache — for repeated reads; use cache-aside before compressing a frequently re-read result
slm-status — check tokens_saved_compress and compress_runs from slm_optimize_stats

SuperLocalMemory v4.1.24 · Qualixar · AGPL-3.0-or-later

Files

Just SKILL.md in plugin/skills/slm-compress of qualixar/superlocalmemory.

Open the folder on GitHubat commit 26f8c68

Compare with similar skills

Slm Compress next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Slm Compress compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Slm Compress this skillqualixar/superlocalmemory	231	—	~1.6k	Automated safety check: Notes	AGPL-3.0	today
Context Mode Output Sandboxmksglu/context-mode	26k	—	~4.1k	Automated safety check: Pass	Custom licence	today
Memori Long-Term MemoryMemoriLabs/Memori	17k	—	~2k	Automated safety check: Notes	Custom licence	6 days ago
Picoclaw Skill Creatorsipeed/picoclaw	30k	—	~4.4k	Automated safety check: Pass	MIT	14 days ago
ccc Semantic Code Searchcocoindex-io/cocoindex-code	2.8k	—	~938	Automated safety check: Pass	Apache-2.0	2 days ago
Context Mode for Antigravity CLImksglu/context-mode	26k	—	~850	Automated safety check: Pass	Custom licence	today

Similar skills

Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
26k GitHub stars~4.1k tokensUpdated today
Agent WorkflowsAuto-check passed
Memori Long-Term Memory
MemoriLabs/Memori
Connects Claude Code to Memori Cloud for long-term memory, recalling stored context before substantive replies and saving new context afterward.
17k GitHub stars~2k tokensUpdated 6 days ago
Agent WorkflowsAuto-check: notes
Picoclaw Skill Creator
sipeed/picoclaw
Guidance for creating, updating and reviewing Picoclaw skills, from the SKILL.md structure to organizing bundled scripts, references and assets.
30k GitHub stars~4.4k tokensUpdated 14 days ago
Agent WorkflowsAuto-check passed
ccc Semantic Code Search
cocoindex-io/cocoindex-code
Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.
2.8k GitHub stars~938 tokensUpdated 2 days ago
Agent WorkflowsAuto-check passed
Context Mode for Antigravity CLI
mksglu/context-mode
Routing rules for using context-mode MCP tools in Antigravity CLI: sandboxed code runs, file analysis, indexed search and web fetches that keep large output out of the conversation.
26k GitHub stars~850 tokensUpdated today
Agent WorkflowsAuto-check passed
Token Optimizer
alexgreensh/token-optimizer
Audit a Claude Code or Codex setup for context-window waste, then fix it and measure the savings.
2.5k GitHub stars~3.6k tokensUpdated yesterday
Agent WorkflowsAuto-check passed

Questions about Slm Compress

What does Slm Compress do?

Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slmcompress(content, mode, reversible, ttlseconds) to shrink content…. Slm Compress is an agent skill from qualixar/superlocalmemory. Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slmcompress(content, mode, reversible, ttlseconds) to shrink content; if the result is lossy a ccrid is returned so you can call slmretrieve(ccrid) later to recover the exact original; always fail-open (ok:false → continue with the original).

When should I use Slm Compress?

Slm Compress fits situations like: tasks that involve Context engineering.

How do I install Slm Compress in Claude Code?

Run `npx skills add qualixar/superlocalmemory --skill slm-compress -a claude-code`. Or copy the skill folder (plugin/skills/slm-compress in qualixar/superlocalmemory) into .claude/skills/slm-compress in your project. Claude Code loads it when a task matches its description.

How do I install Slm Compress in Codex?

Run `npx skills add qualixar/superlocalmemory --skill slm-compress -a codex`. Or copy the skill folder (plugin/skills/slm-compress in qualixar/superlocalmemory) into .agents/skills/slm-compress in your project. Codex loads it when a task matches its description.

Can I use Slm Compress in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qualixar/superlocalmemory --skill slm-compress -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/slm-compress, .gemini/skills/slm-compress, .github/skills/slm-compress and .opencode/skills/slm-compress in your project.

What does Slm Compress need to run?

SKILL.md names no scripts, command-line tools or credentials: Slm Compress is instructions for the agent only. Our summary lists: Python 3. Its frontmatter pre-approves these tools: slm_compress, slm_retrieve, Bash.

Does Slm Compress access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Slm Compress safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Slm Compress use?

Slm Compress is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Slm Compress use?

About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Slm Compress?

Skills that share tags, products or a category with Slm Compress: Context Mode Output Sandbox (mksglu/context-mode, 26k stars), Memori Long-Term Memory (MemoriLabs/Memori, 17k stars), Picoclaw Skill Creator (sipeed/picoclaw, 30k stars) and ccc Semantic Code Search (cocoindex-io/cocoindex-code, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Slm Compress?

qualixar (a GitHub organization) maintains it in qualixar/superlocalmemory, which has 231 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 9, 2026.

Source: qualixar/superlocalmemory on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Slm Compress

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

slm-compress — Reversible Context Compression (Surface B)

Purpose

Primary MCP Tool: slm_compress

Return dict (all keys always present)

Mode semantics (verified from source)

Recovery Tool: slm_retrieve

CCR security rule

Decision: When to Compress

Fail-Open Guarantee

Worked Example

Secondary CLI (fallback when MCP is unavailable)

Size Cap

Related skills

Files

Compare with similar skills

Similar skills

More from qualixar/superlocalmemory

Related

Questions about Slm Compress