agentmods.dev

squish

A command for finding and opening earlier AI coding sessions saved in Squish memory.

In plain words
What is it for?
Use it to list sessions, search by topic or tags, open a session by ID, find sessions related to recently changed files, or save a session summary.
Why use it?
It helps you recover past decisions, errors, changed files, and unfinished tasks without searching through old conversations manually.

Command

11 6d ago A scan 11 tokens original MIT
View the source file michielhdoteth/squish-memory
Install

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.

agentmods
npx agentmods add commands/michielhdoteth/squish-memory/squish
Clone the repo
git clone --depth 1 https://github.com/michielhdoteth/squish-memory
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 461 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00461
Opus 5 $0.00005 $0.00230
Sonnet 5 $0.00002 $0.00092
Haiku 4.5 $0.00001 $0.00046

Measured 2d ago against content hash e2d79b2ef282, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

squish 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 2d 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.

plugin/opencode/commands/squish.md · 39 lines

What it actually says

You are the Squish session memory tool. The user invoked /squish $ARGUMENTS.

Parse the arguments as ONE of these subcommands (case-insensitive):

  1. sessions (no args or list):

    • Run: squish sessions list --json
    • Present a compact table: id, title, project, status, ended_at
    • Offer to search or load a specific one

  2. search <query>:

    • Run: squish sessions search "<query>" --json (escape the query as a shell-safe string)
    • If tags are also present in args (after --tag), add --tag t1,t2
    • Present the top 10 results as ranked cards

  3. load <id> or show <id>:

    • Run: squish sessions show <id> --json
    • Present the full session detail: title, summary, project, branch, dates, files_touched (all), decisions, errors, todos

  4. related:

    • Run: squish sessions related --json (the CLI auto-detects repo_path from cwd and uses recently-touched files from git)
    • Present the top 5 related sessions
    • If no results, suggest squish sessions search "<topic>" instead

  5. capture <summary>:

    • Run: squish sessions capture "<summary>" --json
    • If the user provided --title T or --tags t1,t2 etc, forward them
    • Confirm the saved id and offer to add tags/files

Note (v1.5.5): the legacy inject <id> subcommand has been removed. The agent has bash + code execution and can call squish sessions search "<query>" --json directly to pull past session content. The squish_session_inject plugin tool has been removed for the same reason.

Changes

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.

  1. 2d ago First seen · 39 lines · 11 tokens per session scan A e2d79b2ef282

Subscribe to this mod's changes

squish is a command published in the GitHub repository michielhdoteth/squish-memory (11 stars, last pushed 6d ago), licensed MIT. It adds 11 tokens to every session and 461 once invoked, about $0.0001 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.

Memory and contextagent-memoryai-agentmcppersistent memorysqlite
Related

Other commands, from other repositories

tokenless-stats

Show Tokenless compression statistics.

alibaba/anolisa · 10 tokens

arrecall

AgentRecall on-demand recall — surface past fixes, decisions, and patterns mid-session without leaving your flow.

Goldentrii/AgentRecall-X · 21 tokens

evolve-lite-subscribe

Add a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.

AgentToolkit/altk-evolve · 23 tokens

image-node-intake

Parse a visual brief into the Image Node Factory intake JSON.

TheSmokeDev/taskchad-os · 12 tokens

execute

Execute an implementation plan.

TheSmokeDev/taskchad-os · 4 tokens

csm-governance

Run memory governance — dedup detection, candidate and archive reports, merges.

NovasPlace/CSM · 15 tokens