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-claude-plugin/tree-ring-capturegit clone --depth 1 https://github.com/TerminallyLazy/tree-ring-memory-claude-pluginWrote 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.
[](https://agentmods.dev/commands/terminallylazy/tree-ring-memory-claude-plugin/tree-ring-capture)<a href="https://agentmods.dev/commands/terminallylazy/tree-ring-memory-claude-plugin/tree-ring-capture"><img src="https://agentmods.dev/badge/commands/terminallylazy/tree-ring-memory-claude-plugin/tree-ring-capture.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00013 | $0.00560 |
| Opus 5 | $0.00006 | $0.00280 |
| Sonnet 5 | $0.00003 | $0.00112 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
tree-ring-capture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
89% identical to tree-ring-capture — 37 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Tree Ring Capture
Capture only durable, useful memory. Do not store transcripts, secrets, credentials, raw chain-of-thought, or unverified claims as truth.
Read project-local .tree-ring/SKILL.md and .tree-ring/CLI.md first when
present. Follow the skill's Runtime Bootstrap And Updates procedure and confirm
the selected project-local or global binary reports 0.15.0 or newer. Bootstrap
or upgrade when the user's request already authorizes it; otherwise obtain
permission before downloading or changing software. Never invent a stored
memory.
For a single agent or a store in Open mode, use the user's argument as the memory summary:
tree-ring remember "$ARGUMENTS" \
--event-type lesson \
--scope project
For an ordinary worker in Coordinated mode, use agent scope with the server/task-derived identity and stable retry metadata:
tree-ring remember "$ARGUMENTS" \
--event-type lesson \
--scope agent \
--agent-profile "$TREE_RING_AGENT_PROFILE" \
--workflow-id "$TREE_RING_WORKFLOW_ID" \
--session-id "$TREE_RING_SESSION_ID" \
--operation-id "<stable logical write id>" \
--source-ref "<durable task, run, or result reference>"
Do not invent identity values. Reuse the same session and operation IDs only
for an exact retry; conflicting reuse fails closed. Keep
TREE_RING_COORDINATOR_TOKEN unset in ordinary worker environments.
Adjust --event-type, scope, project, identity, source, and tags to match the
actual memory:
decisionfor selected architecture, release, storage, or policy choiceslessonfor validated work patternswarningfor failures and regressions to avoiduser_preferencefor durable user preferenceshypothesisfor future work that should be revisited as a seed
If the memory comes from a run, test, evaluation, incident, PR, or checkpoint,
prefer tree-ring evidence with an --evidence-ref and outcome.
In Coordinated mode, project/shared writes, tree-ring evidence, heartwood,
and lifecycle mutations require the one-time coordinator capability already
present only in the coordinator process environment. Never put its value in the
prompt, a CLI argument, memory, logs, source references, or committed files.
The shared-root concurrency contract covers cooperative processes on one host and a local filesystem. Identity and scope are routing fields, not read ACLs.
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.
- 3d ago First seen · 65 lines · 13 tokens per session scan A a999f3c6a1d0
tree-ring-capture is a command published in the GitHub repository TerminallyLazy/tree-ring-memory-claude-plugin (0 stars, last pushed 9d ago), licensed MIT. It adds 13 tokens to every session and 560 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to tree-ring-capture, differing in 37 lines, and is treated as a copy.
Other commands, from other repositories
recall
Search the engineering memlog and inject the top matching prior lessons. Use when you suspect a recurring issue.
weekly
Weekly memory report — facts learned, procedures, repeated mistakes prevented.
evolve-lite-adapt-memory
Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable.
status
Show memex statistics and status including projects, memos, and pending items.
jarvis-setup
Launch the local setup page to configure the Jarvis memory hub.
promote
Move .memory/ artifacts to permanent knowledge locations.