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/cbuntingde/kimi-memory/reset-projectgit clone --depth 1 https://github.com/cbuntingde/kimi-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 | $0.00025 | $0.00504 |
| Opus 5 | $0.00013 | $0.00252 |
| Sonnet 5 | $0.00005 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
reset_project 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 yesterday.
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.
What it actually says
/kimi-memory:reset_project
Wipe every per-project row (memories, working memory, conversations, conversation events, edges, synthesizes) for the active project so the project starts from a clean slate. Use this after a repo is re-cloned to the same canonical path: the project_key is a hash of the path, so kimi-memory cannot otherwise tell the new project apart from the old one. The global database and every other project DB are never touched.
Steps:
- Call
memory_reset_projectwithcwdset to the project root andconfirm: falseto do a dry run. Echo the returnedrow_countsandrecloneso the user can see what would be deleted. - Render a one-line confirmation prompt that names the project root, the total row count, and asks for the user's explicit "yes" before continuing. Never auto-confirm — the reset is destructive.
- If the user confirms, call
memory_reset_projectagain withconfirm: trueand echo the returnedsummary(memories_deleted, working_memory_deleted, conversations_deleted, etc.). - If the user declines, stop and report that the project was not
reset. Suggest
/kimi-memory:list_memoriesso the user can see what would have been wiped.
The hook layer surfaces a [stale-memory] line on SessionStart and
UserPromptSubmit when a re-clone is detected (compare directory
birthtime with first_seen_at). Treat that as the trigger to suggest
this command rather than auto-running it.
Example dry run response:
{
"operation": "reset_project_dry_run",
"project_key": "152cb83a2d1f7821",
"reclone": { "isReclone": true, "reason": "directory birthtime is 42m newer than first_seen_at" },
"row_counts": { "memories": 12, "working_memory": 1, "conversations": 9, ... },
"total_rows": 23
}
The plugin's /reset_project skill is equivalent; this command is the
namespaced fallback (/kimi-memory:reset_project).
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.
- yesterday First seen · 49 lines · 25 tokens per session scan A d8ba9b8928f1
reset_project is a command published in the GitHub repository cbuntingde/kimi-memory (0 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 504 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 2026-08-31.
Other commands, from other repositories
tree-ring-capture
Capture a concise validated lesson decision warning or preference in Tree Ring Memory.
tree-ring-audit
Audit consolidate or forget stale sensitive or superseded Tree Ring Memory entries.
tree-ring-update
Check for or install a verified Tree Ring Memory CLI update without changing installation scope.
tree-ring-certify
Generate Tree Ring harness or recall-quality evidence without confusing it with the full framework release suite.
tree-ring-dox-sync
Preview and synchronize DOX-style AGENTS.md guidance as source-linked Tree Ring memory.
tree-ring-recall
Recall durable Tree Ring Memory context before starting or resuming work.