tree-ring-recall

tree-ring-recall is a command for coding agents from TerminallyLazy/Tree-Ring-Memory. It costs 12 tokens per session (417 once invoked), scanned A, original, MIT.

A command for recalling durable project memory before starting or resuming work. It checks project-specific guidance and retrieves relevant previously saved context.

In plain words
What is it for?
Use it at the beginning of context-dependent tasks, when resuming work, or in coordinated workers that need to recall project, workflow or session-specific information.
Why use it?
It reduces repeated discovery work and helps avoid acting without important project context. It also requires checking that the selected Tree Ring tool is sufficiently up to date.

Command

Part of the tree-ring-memory plugin — 1 skill, 7 commands shipped together

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/terminallylazy/tree-ring-memory/tree-ring-recall
Clone the repo
git clone --depth 1 https://github.com/TerminallyLazy/Tree-Ring-Memory

Or install tree-ring-memory, the plugin that ships this one along with the rest of its 1 skill, 7 commands.

Wrote 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.

agentmods badge for tree-ring-recall

README.md
[![agentmods](https://agentmods.dev/badge/commands/terminallylazy/tree-ring-memory/tree-ring-recall.svg)](https://agentmods.dev/commands/terminallylazy/tree-ring-memory/tree-ring-recall)
Your own site
<a href="https://agentmods.dev/commands/terminallylazy/tree-ring-memory/tree-ring-recall"><img src="https://agentmods.dev/badge/commands/terminallylazy/tree-ring-memory/tree-ring-recall.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 417 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 $0.00012 $0.00417
Opus 5 $0.00006 $0.00209
Sonnet 5 $0.00002 $0.00083
Haiku 4.5 $0.00001 $0.00042

Measured 3d ago against content hash 61b94d6f5689, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tree-ring-recall 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/tree-ring-memory/commands/tree-ring-recall.md · 50 lines

What it actually says

Tree Ring Recall

Recall useful project memory before acting on context-dependent work.

  1. Check for project-local guidance first:

    test -f .tree-ring/SKILL.md && sed -n '1,520p' .tree-ring/SKILL.md
    test -f .tree-ring/CLI.md && sed -n '1,520p' .tree-ring/CLI.md
    

    Follow the skill's Runtime Bootstrap And Updates procedure and confirm the selected binary reports 0.15.0 or newer. Bootstrap or upgrade when the user's request already authorizes it; otherwise obtain permission before downloading or changing software. Never fabricate recall.

  2. Use the user's argument as the focused recall query when present:

    tree-ring recall "$ARGUMENTS"
    
  3. If no argument is provided, choose a narrow query from the current task and include project scope when known.

  4. In a fan-out worker, filter recall with its agent profile plus the shared workflow and current session. At coordinator fan-in, omit only the agent-profile filter deliberately so all worker results remain visible:

    env -u TREE_RING_AGENT_PROFILE tree-ring recall "$ARGUMENTS" \
      --workflow-id "$TREE_RING_WORKFLOW_ID" \
      --session-id "$TREE_RING_SESSION_ID" \
      --scope agent
    
  5. Treat recall as context, not authority. Prefer source-linked, high-confidence, non-superseded entries and verify drift-prone facts before relying on them.

Identity and scope partition and route local memory; they are not read ACLs. The supported shared-root boundary is cooperative processes on one host and a local filesystem, not cross-host or network-filesystem coordination.

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. 3d ago First seen · 50 lines · 12 tokens per session scan A 61b94d6f5689

Subscribe to this mod's changes

tree-ring-recall is a command published in the GitHub repository TerminallyLazy/Tree-Ring-Memory (16 stars, last pushed 5d ago), licensed MIT. It adds 12 tokens to every session and 417 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.