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 skills/cbuntingde/kimi-memory/reset_projectnpx skills add cbuntingde/kimi-memory --skill reset_projectgit clone --depth 1 https://github.com/cbuntingde/kimi-memoryWrote 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/skills/cbuntingde/kimi-memory/reset_project)<a href="https://agentmods.dev/skills/cbuntingde/kimi-memory/reset_project"><img src="https://agentmods.dev/badge/skills/cbuntingde/kimi-memory/reset_project.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 | $0.00055 | $0.00676 |
| Opus 5 | $0.00028 | $0.00338 |
| Sonnet 5 | $0.00011 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
When to use
- The hook layer surfaces a
[stale-memory]line on SessionStart or UserPromptSubmit (compare directory birthtime withfirst_seen_at). - The user says "I re-cloned this repo" / "I deleted and re-cloned" / "the memory is stale" / "start fresh on this project".
memory_statusreportsreclone.isReclone: trueand the user wants to clean up.
Steps
- Call
memory_reset_projectwithcwdset to the project root andconfirm: false(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 and there is no undo.
- If the user confirms, call
memory_reset_projectagain withconfirm: trueand echo the returnedsummary(memories_deleted,working_memory_deleted,conversations_deleted,conversation_events_deleted,memory_edges_deleted,memory_synthesizes_deleted). - 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.
Memory recall and acknowledgement
Before wiping, run memory_recall(scope='project', ...) to surface the durable entries that will go away. Render a one-line summary so the user knows what is being lost (e.g. "3 conventions, 1 procedure, 1 working note will be deleted"). This is the recall acknowledgement contract — the user can read what was on file and make a final call.
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 · 43 lines · 55 tokens per session scan A 3fe209dd4d3e
reset_project is a skill published in the GitHub repository cbuntingde/kimi-memory (0 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 676 once invoked, about $0.0003 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 skills, from other repositories
membrain
Shared long-term memory over MCP. Call memorycontext once at the start of any session/task to load what is already known; use searchmemory before answering questions about the user or their projects; save durable facts, preferences, and decisions with savememory / savememories. All agents and the user share the same…
delx-memory
Local-first agent memory MCP. No API keys. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Delx Memory data or actions through an agent.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
latent-premises
Use when reviewing a diff or module for hidden assumptions - things the code takes for granted that nothing guarantees - or when asked "what could break this later", "what does this assume", or to harden code that works today. Complements bug-hunt: bug-hunt finds defects with triggers today; this finds the ones…
write
Use for marketing, social, replies, product copy, launch copy, and writing in the user's voice when their Emulo writing profile should guide the task. Do not use for unrelated execution or UI/UX design alone.