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.
npx agentmods add commands/terminallylazy/tree-ring-memory/tree-ring-updategit clone --depth 1 https://github.com/TerminallyLazy/Tree-Ring-MemoryWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00015 | $0.00412 |
| Opus 5 | $0.00008 | $0.00206 |
| Sonnet 5 | $0.00003 | $0.00082 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
tree-ring-update 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- tree-ring-update — 100% identical, 0 lines differ
What it actually says
Tree Ring Update
Resolve the real project root and read project-local .tree-ring/SKILL.md and
.tree-ring/CLI.md when present. Prefer .tree-ring/bin/tree-ring for that
project when it exists; otherwise resolve the active global binary with
command -v tree-ring. Use which -a tree-ring to detect older shadowing
copies.
For a read-only release check, run the selected binary:
tree-ring update --check
If the user asked only to check, report the installed version, available
version, executable path, and install method without changing files. If the
user already authorized an update, run tree-ring update; otherwise obtain
permission immediately before the update. The updater must preserve the active
project-local, direct-prefix, or Homebrew scope and verify official release
assets. Never install a second copy merely to bypass an older active binary.
CLIs older than 0.15.0 lack the update command. Upgrade with the same manager or
prefix: brew upgrade tree-ring for Homebrew, the official installer with
--project --release latest for an existing project-local binary, or
--install-dir <existing-prefix> --release latest for another direct install.
Do not change global scope or edit shell startup files without separate user
authorization.
After updating, verify the selected binary with --version, return to the
actual project root, and run:
tree-ring --root .tree-ring init
tree-ring --root .tree-ring integrations status --verbose
Use .tree-ring/bin/tree-ring for both commands when the project has a local
binary. Confirm the files remain under the intended project's .tree-ring/.
Initialization refreshes managed guidance but does not prove harness activation.
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.
- 2d ago First seen · 46 lines · 15 tokens per session scan A 132e1dc17dfe
tree-ring-update is a command published in the GitHub repository TerminallyLazy/Tree-Ring-Memory (16 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 412 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.
Other commands, from other repositories
reconcile
Clear the decision review backlog. Walk the decisions that are due for review and, for each, decide together: still true, needs evidence, changed, or archive.
wrap
Close the session cleanly. Update entity state. Capture decisions. Detect momentum shifts.
focus
"What should I work on today, and why?".
brain
Instant project intelligence. Where things are, what's stale, what decisions are pending, where to go next.
decide
Capture a strategic decision so it never gets lost or reopened accidentally.
graph
Show how entities connect, what they share, and where building one helps another.