Using Agent Skills
addyosmani/agent-skills
Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.
Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that state the same rules: compress wording, delete duplicates and…
Install Squid Clean Memory
$ npx skills add iusztinpaul/squid --skill squid-clean-memory -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install iusztinpaul/squid squid-clean-memory --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/iusztinpaul/squid.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/squid-clean-memory .claude/skills/squid-clean-memory && rm -rf skills-srcUse ~/.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/
Install the "squid-clean-memory" agent skill from https://github.com/iusztinpaul/squid/tree/main/skills/squid-clean-memory into .claude/skills/squid-clean-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "squid-clean-memory", 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 install https://github.com/iusztinpaul/squid/tree/main/skills/squid-clean-memoryType 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.
$ npx skills add iusztinpaul/squid --skill squid-clean-memory -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install iusztinpaul/squid squid-clean-memory --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iusztinpaul/squid.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/squid-clean-memory .agents/skills/squid-clean-memory && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "squid-clean-memory" agent skill from https://github.com/iusztinpaul/squid/tree/main/skills/squid-clean-memory into .agents/skills/squid-clean-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "squid-clean-memory", 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.
$ npx skills add iusztinpaul/squid --skill squid-clean-memory -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install iusztinpaul/squid squid-clean-memory --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iusztinpaul/squid.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/squid-clean-memory .cursor/skills/squid-clean-memory && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "squid-clean-memory" agent skill from https://github.com/iusztinpaul/squid/tree/main/skills/squid-clean-memory into .cursor/skills/squid-clean-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "squid-clean-memory", 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 https://github.com/iusztinpaul/squid.git --path skills/squid-clean-memory--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add iusztinpaul/squid --skill squid-clean-memory -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install iusztinpaul/squid squid-clean-memory --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iusztinpaul/squid.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/squid-clean-memory .gemini/skills/squid-clean-memory && rm -rf skills-srcUse ~/.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/
Install the "squid-clean-memory" agent skill from https://github.com/iusztinpaul/squid/tree/main/skills/squid-clean-memory into .gemini/skills/squid-clean-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "squid-clean-memory", 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.
$ gh skill install iusztinpaul/squid squid-clean-memoryInstalls 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).
$ npx skills add iusztinpaul/squid --skill squid-clean-memory -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/iusztinpaul/squid.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/squid-clean-memory .github/skills/squid-clean-memory && rm -rf skills-srcUse ~/.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/
Install the "squid-clean-memory" agent skill from https://github.com/iusztinpaul/squid/tree/main/skills/squid-clean-memory into .github/skills/squid-clean-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "squid-clean-memory", 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.
$ npx skills add iusztinpaul/squid --skill squid-clean-memory -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install iusztinpaul/squid squid-clean-memory --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iusztinpaul/squid.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/squid-clean-memory .opencode/skills/squid-clean-memory && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "squid-clean-memory" agent skill from https://github.com/iusztinpaul/squid/tree/main/skills/squid-clean-memory into .opencode/skills/squid-clean-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "squid-clean-memory", 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
squid-clean-memory- GitHub stars
- 203
- Token cost
- ~1.3k tokens
- SKILL.md length
- 690 words
- Files
- 1
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that state the same rules: compress wording, delete duplicates and…
- Works in 7 steps: Resolve the target set → Compress wording (caveman pass) → Apply the keep/delete test → …
- Tasks that involve Agent instruction files
- SKILL.md covers When NOT to use, Step 1 — Resolve the target set, Step 2 — Compress wording… and Step 3 — Apply the keep/delete…, plus 5 more sections
- Calls git and uv
What it does
Squid Clean Memory is an agent skill from iusztinpaul/squid. Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that state the same rules: compress wording, delete duplicates and harness-enforced claims, merge fragments.
Its SKILL.md is about 1.3k 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 Agent instruction files. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Agent instruction files
Example prompts
- “/squid-clean-memory”
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit f5bf6b3. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
gituv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git and uv, which can reach the network depending on how they are called.
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
Squid Clean Memory loads about 1.3k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 690 words of instructions outside code blocks.
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 passed
The automated check found no risky patterns in SKILL.md.
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 iusztinpaul/squid at commit f5bf6b3, republished under its Apache-2.0 licence (© iusztinpaul). 690 words, ~1,315 tokens.
Download SKILL.mdSave it as
.claude/skills/squid-clean-memory/SKILL.md (or your agent's skills folder).- name
- squid-clean-memory
- description
- Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that state the same rules: compress wording, delete duplicates and harness-enforced claims, merge fragments.
- disable-model-invocation
- true
- argument-hint
- [scope-path] (default: every memory file in the repo)
Clean memory — same rules, minimum words
You are the cleaner. You shrink the memory files sessions load; you do not change what they instruct. Zero meaning diff is the contract — every rule that holds before must hold after, and no new rule may appear.
$ARGUMENTS is an optional file or directory scope. Empty means every memory file in the repo: the
root AGENTS.md plus each nested AGENTS.md / CLAUDE.md. Where CLAUDE.md symlinks AGENTS.md,
that is one file — edit the target, never replace the symlink with a copy.
When NOT to use
- Docs, READMEs, comments, docstrings →
/squid-clean-docs. - A rule you think is wrong — that is a deliberate edit to make with the user, not a cleanup.
Step 1 — Resolve the target set
Discover the set with git ls-files '*AGENTS.md' '*CLAUDE.md' (tracked files only, so vendored trees
stay out), narrow to $ARGUMENTS if given, and collapse symlink pairs. The files must be clean in
git.
Step 2 — Compress wording (caveman pass)
If the caveman plugin is installed, ask, then run /caveman-compress <file> on each file in the set
and commit the pass as one commit (code, paths, and URLs are byte-preserved). Compress before cutting:
normalised wording turns reworded duplicates into literal ones. Not installed → skip; the cuts below
still shrink the files, just without the wording-level pass.
Step 3 — Apply the keep/delete test
A memory line survives only if deleting it would change how a future session behaves. Three cuts:
Duplicates — the same instruction stated twice, even reworded — in one file or across the set: a
nested AGENTS.md repeating the root dies where it's nested, since the root already loads everywhere.
Keep one home, delete the copies; leave a cross-reference only when the section survives without it.
Moving a rule between files (root ↔ nested) changes where it applies — that is a scope edit, not a
cleanup: flag it in the plan, never fold it into a dedupe.
Baked-in claims — the test: would a fresh session with an empty memory file already behave this
way? If yes, the line is dead weight. Caution: AGENTS.md is read by non-Claude harnesses too — if
the behaviour is a Claude Code default rather than universal, keep the line and flag it in the plan.
| Delete | Keep |
|---|---|
| "Always read a file before modifying it." — harness enforces | "Use uv run pytest, never bare pytest." — project decision |
| "Be concise." / "Don't over-engineer." — system-prompt defaults | "Chunk at 200 tokens — the embedding model truncates above 256." |
| Install steps under both Setup and Contributing — one home | "Never edit docs/adr/ — ADRs are immutable." |
Merges — two sections merge when a reader never needs one without the other, or a section is a few lines sharing a topic with its neighbour. A 3-line Code style plus a 2-line Naming become one Conventions; a heading costs more attention than it organises.
Show full SKILL.md (228 more words)Show less
Step 4 — Plan of attack (the output artifact)
Print one table in chat. Do not write it to disk unless the user asks.
| File | Lines / section | Cut (Step 3) | Why | ~Words |
|---|---|---|---|---|
AGENTS.md | "read before you edit" | baked-in | harness enforces it | −9 |
api/AGENTS.md | "use uv run, never pip" | duplicate | root already states it | −11 |
AGENTS.md | Code style + Naming | merge | always read together | −12 |
Stop and wait for explicit approval. Do not edit before it.
Step 5 — Execute
Apply the approved plan as one commit, separate from the Step 2 commit.
Step 6 — Verify
Meaning must be provably unchanged before hand-off:
- Re-read each final file against its pre-clean version: every old rule is still stated in a file that loads wherever the rule applied, merged, or a planned deletion — name its new home.
- Every path, command, and URL in the files still resolves.
git difftouches only memory files.
Anything off: revert that commit, do not "fix forward".
Step 7 — Hand-off
Report wc -w before → after per file. Then ask the user to run /doctor (Claude Code only — a
built-in you cannot invoke): Step 1 scopes this pass to tracked files, so the always-loaded
local ones — ~/.claude/CLAUDE.md, CLAUDE.local.md — are never reached here; /doctor
dedupes those against the checked-in set.
Notes on shape
- Fewer words, never fewer rules. If a cut loses a nuance, it is an edit — out of scope.
© iusztinpaul, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/squid-clean-memory of iusztinpaul/squid.
Open the folder on GitHubat commit f5bf6b3
Compare with similar skills
Squid Clean Memory 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Squid Clean Memory this skilliusztinpaul/squid | 203 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Using Agent Skillsaddyosmani/agent-skills | 103k | 4 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Claude ReflectBayramAnnakov/claude-reflect | 1.7k | 2 repos | ~627 | Automated safety check: Pass | MIT | |
| Writing For Agentsbestofjs/bestofjs | 3.1k | 19 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
Claude Reflect
BayramAnnakov/claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.
Writing For Agents
bestofjs/bestofjs
Writing documents for agents. An agent skill from bestofjs/bestofjs.
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
- Official
SkillOpt Sleep Cycle
microsoft/SkillOpt
Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.
More from iusztinpaul/squid
All 13 skills in this repoSquid Implement Night
iusztinpaul/squid
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR.
Squid Implement Task
iusztinpaul/squid
Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS.
Squid Review
iusztinpaul/squid
Push the committed feature branch, create or update its PR, then run Product Architect acceptance and PR-Reviewer on it.
Squid Review CI
iusztinpaul/squid
Drive CI green on a pushed, review-clean feature PR — On-Call diagnoses failures and hands fix tasks to the SWE.
Squid Testing Python
iusztinpaul/squid
Write and evaluate effective Python tests using pytest. An agent skill from iusztinpaul/squid.
Squid Architecture Review
iusztinpaul/squid
Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly.
Related
Categories
Questions about Squid Clean Memory
What does Squid Clean Memory do?
Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that state the same rules: compress wording, delete duplicates and…. Squid Clean Memory is an agent skill from iusztinpaul/squid.md — to the minimum words that state the same rules: compress wording, delete duplicates and harness-enforced claims, merge fragments.
When should I use Squid Clean Memory?
Squid Clean Memory fits situations like: tasks that involve Agent instruction files.
How do I install Squid Clean Memory in Claude Code?
Run `npx skills add iusztinpaul/squid --skill squid-clean-memory -a claude-code`. Or copy the skill folder (skills/squid-clean-memory in iusztinpaul/squid) into .claude/skills/squid-clean-memory in your project. Claude Code loads it when a task matches its description.
How do I install Squid Clean Memory in Codex?
Run `npx skills add iusztinpaul/squid --skill squid-clean-memory -a codex`. Or copy the skill folder (skills/squid-clean-memory in iusztinpaul/squid) into .agents/skills/squid-clean-memory in your project. Codex loads it when a task matches its description.
Can I use Squid Clean Memory 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 iusztinpaul/squid --skill squid-clean-memory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/squid-clean-memory, .gemini/skills/squid-clean-memory, .github/skills/squid-clean-memory and .opencode/skills/squid-clean-memory in your project.
What does Squid Clean Memory need to run?
Going by SKILL.md and its folder, Squid Clean Memory needs the command-line tools its instructions call (git and uv).
Does Squid Clean Memory access the network?
SKILL.md contains no URLs. Its commands use git and uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Squid Clean Memory safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Squid Clean Memory use?
Squid Clean Memory is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Squid Clean Memory use?
About 1.3k tokens (SKILL.md is roughly 5.3k 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 Squid Clean Memory?
Skills that share tags, products or a category with Squid Clean Memory: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Squid Clean Memory?
iusztinpaul (a GitHub user) maintains it in iusztinpaul/squid, which has 203 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 3, 2026.
Source: iusztinpaul/squid on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.