agentmemory is a persistent-memory system that lets AI coding agents retain and search information across sessions. It connects with several coding agents and MCP clients, storing knowledge with confidence scoring, lifecycle handling, knowledge graphs, and hybrid search. The catalogue contains agentmemory integrations such as skills, hooks, commands, a plugin, and an MCP component.
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 skills add rohitg00/agentmemory --skill forgetgit clone --depth 1 https://github.com/rohitg00/agentmemoryWrote 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/rohitg00/agentmemory/forget)<a href="https://agentmods.dev/skills/rohitg00/agentmemory/forget"><img src="https://agentmods.dev/badge/skills/rohitg00/agentmemory/forget/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rohitg00/agentmemory/forget"><img src="https://agentmods.dev/badge/skills/rohitg00/agentmemory/forget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 3 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 5.1 | $0.00044 | $0.00673 |
| Opus 5.5 | $0.00018 | $0.00269 |
| Sonnet 5.5 | $0.00009 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
forget 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 14d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user wants to remove data from agentmemory: $ARGUMENTS
Quick start
memory_smart_search { "query": "old api key in config", "targetLayer": "memory", "limit": 20 }
Show the matches, get a yes, then:
memory_governance_delete { "memoryIds": "abc12345,def67890", "reason": "user privacy request" }
Expected output:
Found 2 matching memories. Confirmed. Deleted 2 memories.
Why
This is destructive and irreversible. Show exactly what will be deleted and get an explicit yes before calling delete. Delete by memory ID, never a bare session.
Workflow
- Search with
memory_smart_search, the user's text asquery,targetLayer: "memory",limit: 20, and the requested project/agent scope. These are selected relevance matches, not an exhaustive inventory. - Show what matched: memory ids, titles, and scope. Redact secret values. Ask for explicit confirmation. Do not proceed on silence or a vague "sure, whatever".
- On confirmation, call
memory_governance_deletewithmemoryIdsas a comma-separated string and optionalreason(defaultplugin skill request). - Observation or whole-session erasure is not supported by this operation.
Explain that limit before proceeding; never label selected memory deletion
as a complete session wipe. Do not pass observation IDs or a
sessionId. - Lessons are separate: delete one with
memory_lesson_deleteand itslessonId;memory_governance_deletedoes not touch lessons. - Check
deleted,notFound, andfailedin the response. Report actual deletions and unresolved IDs separately. Recheck the selected IDs before retrying a failed request; an interrupted response may hide a completed write.
Anti-patterns
WRONG: search returns matches, you immediately call memory_governance_delete
without showing them or waiting for a yes.
RIGHT: list the matches, ask "Delete these 2? (yes/no)", and only delete after an explicit yes.
Checklist
- Matches were shown to the user before any delete.
- An explicit yes was received, not assumed.
memoryIdsholds real ids from the search, never a baresessionId.- Final message states the actual count deleted.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 14d ago Changed · +4 lines · +1 tokens per session 10f1c346c669
- 1mo ago First seen · 70 lines · 43 tokens per session scan A 4578899d32c2
forget is a skill published in the GitHub repository rohitg00/agentmemory (29,952 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 673 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
memory-retain
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…
md-fetch-summarize
Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of ". Proactively suggest when the user pastes a URL and asks what it…
session-summaries
What the chat right-panel session summary shows, what it costs, and how to make a session summarize well. Load when the user asks about the session summary panel, why a summary looks wrong or empty, or how to turn it on.