tree-ring-audit

A command set for reviewing, consolidating, or removing outdated, sensitive, or replaced entries in Tree Ring Memory, a local project-memory system for coding agents.

In plain words
What is it for?
Use it when work ends, privacy is a concern, or stored information may be outdated. It supports memory audits, consolidation previews, maintenance, and focused review.
Why use it?
It helps prevent old or private information from remaining in the agent's stored project memory. It also checks the memory tool's version and backup requirements before changes.

Command

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-audit
Clone the repo
git clone --depth 1 https://github.com/TerminallyLazy/Tree-Ring-Memory
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 565 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 $0.00013 $0.00565
Opus 5 $0.00006 $0.00282
Sonnet 5 $0.00003 $0.00113
Haiku 4.5 $0.00001 $0.00056

Measured 2d ago against content hash dd0446c40ff5, 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-audit 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/tree-ring-memory/commands/tree-ring-audit.md · 67 lines

What it actually says

Tree Ring Audit

Audit memory when work is closing, when privacy may matter, or when older entries may be stale.

Read project-local .tree-ring/SKILL.md and .tree-ring/CLI.md first when present. Follow the skill's Runtime Bootstrap And Updates procedure and confirm the selected project-local or global 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 invent results.

Before any current command other than policy status or policy audit opens an existing pre-v0.13 store, stop every Tree Ring process, checkpoint and back up the complete store, and upgrade every CLI, plugin, and bundled worker. All mixed-version operation is unsupported.

These policy preflight commands never create or migrate a store:

tree-ring policy status
tree-ring policy audit --limit 100

After the verified schema-v3 upgrade, start with non-mutating inspection:

tree-ring audit --audit-type sensitive
tree-ring consolidate --period-type manual --dry-run
tree-ring maintain

If the user names a focus, use it to narrow recall before changing memory:

tree-ring recall "$ARGUMENTS"

Use explicit forget operations only when justified:

tree-ring forget mem_example --mode redact --reason "remove sensitive detail"
tree-ring forget mem_example --mode delete --reason "should not be retained"

The CLI forget modes are redact and delete. For an explicit supersession, use the TUI's /supersede <old_id> lifecycle action. Clarify the exact memory identifier and mutation before running any lifecycle write.

In Coordinated mode, forget/redact, supersede, persisted consolidation, and applied maintenance such as --repair-fts require TREE_RING_COORDINATOR_TOKEN in the coordinator process environment. Never put the capability value in a prompt, CLI argument, memory, log, source reference, or committed file. policy status, policy audit, ordinary audit, consolidation dry-run, and plain maintain do not change memory content on an already-upgraded schema-v3 store. Only the two policy commands are guaranteed not to create or migrate a store.

Do not delete, redact, or supersede memory without a clear reason. The coordinator policy is not a read ACL, and its shared-root support is bounded to cooperative processes on one host using a local filesystem.

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 · 67 lines · 13 tokens per session scan A dd0446c40ff5

Subscribe to this mod's changes

tree-ring-audit is a command published in the GitHub repository TerminallyLazy/Tree-Ring-Memory (16 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 565 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.