tree-ring-certify

A command set for producing evidence about Tree Ring Memory's agent harness or the quality of recalled context. An agent harness is the setup that connects an agent to supporting tools or workflows.

In plain words
What is it for?
Use it to run harness-integration or recall-quality checks and record pass, fail, or skipped results in the project's certification folder.
Why use it?
It separates focused evidence checks from the project's full release test suite, so results are not mistaken for proof that an agent actually used recalled information.

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-certify
Clone the repo
git clone --depth 1 https://github.com/TerminallyLazy/Tree-Ring-Memory
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 338 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 $0.00017 $0.00338
Opus 5 $0.00009 $0.00169
Sonnet 5 $0.00003 $0.00068
Haiku 4.5 $0.00002 $0.00034

Measured 2d ago against content hash b1ff689759c9, 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-certify 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-certify.md · 35 lines

What it actually says

Tree Ring Certify

Read project-local .tree-ring/SKILL.md and .tree-ring/CLI.md when present, then 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 invent certification results.

For an installed runtime, choose the requested self-contained evidence path:

tree-ring integrations certify --source-root <project-root>
tree-ring recall-quality --source-root <project-root>

Default to harness certification and the current project root. Report the observed pass/fail/skip counts, evidence directory, and any next steps. These commands write evidence under target/tree-ring-certification/, but they do not activate a harness or prove that an agent used recalled context; check receipt-backed integration status separately.

The full sh scripts/certify-tree-ring.sh release suite is repository-only. Run it only when the current directory is a canonical Tree Ring Memory source checkout containing that script, the Rust workspace, install.sh, fixtures, and build tooling. Never copy or download the script into another project and never represent the installed CLI checks as full framework release certification. The TUI's /evidence refresh action only displays that external command; it does not execute the suite.

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 · 35 lines · 17 tokens per session scan A b1ff689759c9

Subscribe to this mod's changes

tree-ring-certify is a command published in the GitHub repository TerminallyLazy/Tree-Ring-Memory (16 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 338 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.