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-capturegit 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 | $0.00013 | $0.00921 |
| Opus 5 | $0.00006 | $0.00461 |
| Sonnet 5 | $0.00003 | $0.00184 |
| Haiku 4.5 | $0.00001 | $0.00092 |
Grade A, and why
tree-ring-capture 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-capture — 89% identical, 37 lines differ
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tree Ring Capture
Capture only durable, useful memory. Do not store transcripts, secrets, credentials, raw chain-of-thought, or unverified claims as truth.
Lifecycle Stop Checkpoint
Stop and SubagentStop hooks enforce one agent-mediated checkpoint. The hook
never inspects or persists transcript_path, last_assistant_message, prompts,
or transcript content. Evaluate the grounded work already in the active agent's
context. If there is no durable, normal-sensitivity candidate, do not write a
memory.
For each qualifying candidate, use the exact identity-bound template returned by the lifecycle handler. Its strict shape is:
tree-ring --root .tree-ring capture "<concise summary>" \
--event-type <preference|decision|lesson|warning|correction|seed> \
--ring <cambium|scar|seed> \
--project <project> \
--agent-profile <profile> \
--workflow-id <workflow> \
--session-id <session> \
--operation-id auto-<checkpoint>-<1..3> \
--source-ref agent-checkpoint:<checkpoint> \
[--tag <tag>]
Do not invent or edit the supplied identity, checkpoint, operation, or source
values. Strict capture fixes scope=agent, requires identity and provenance,
adds the automatic-capture tag, and accepts normal sensitivity only. Use no more
than three candidates in the single checkpoint. Never replace this with a raw
transcript summary, remember, evidence, or an import.
Use cambium for preferences, decisions, lessons, and corrections; scar for
warnings; and seed for future work. A candidate still must be durable and
grounded regardless of its ring.
The manual command flow below remains available for an explicit user-directed capture outside a lifecycle checkpoint.
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 a stored
memory.
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 · 102 lines · 13 tokens per session scan A a5c746323caa
tree-ring-capture is a command published in the GitHub repository TerminallyLazy/Tree-Ring-Memory (16 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 921 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
recall
Search past session observations and lessons for relevant context. Wrap the memorysmartsearch and memorylessonrecall MCP tools.
remember
Explicitly save an insight, decision, or learning to agentmemory for future sessions. Wraps the memorysave MCP tool.
recall
Search past session observations and lessons for relevant context. Wrap the memorysmartsearch and memorylessonrecall MCP tools.
reindex
Idempotent reindex of an existing course — rewrite retired coverage.md tier markers to canonical vocabulary and materialize errors/log.md nature/phase into the on-disk schema (header keys == data keys), in place and atomically, WITHOUT running analyze.
alt
Import an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam signal into the course index — radar.md, a lecture-emphasis column on coverage.md, and a gold-zone weakmap.
blind
Strategy-level blind drill on a known HW or example problem. User describes approach in prose (no math typing); Claude verifies against solution then saves clean reference to derivations/.