agentmods.dev

Memory recall

Memory recall is a skill for Claude Code, Codex from pincerhq/pincer. It costs 54 tokens per session (411 once invoked), scanned A, original, MIT.

A guide to Pincer's long-term memory, which stores short facts, preferences, and past context separately from the current chat. It explains when to search those stored memories explicitly.

In plain words
What is it for?
Use it when someone asks what Pincer remembers, refers to a specific earlier conversation, or needs a broader search of stored user information.
Why use it?
It helps the agent answer questions about earlier conversations without assuming that the current chat contains the full history. It also clarifies that memories are brief facts, not complete transcripts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 44repo +2 yesterday A scan SkillSpector: pass 54 tokens original MIT

Good fit Use it when someone asks what Pincer remembers, refers to a specific earlier conversation, or needs a broader search of stored user information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pincerhq/pincer/memory-recall
View source ↗ pincerhq/pincer
Install

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.

Any agent
npx skills add pincerhq/pincer --skill memory-recall
Clone the repo
git clone --depth 1 https://github.com/pincerhq/pincer

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Memory recall

README.md
[![agentmods](https://agentmods.dev/badge/skills/pincerhq/pincer/memory-recall/github.svg)](https://agentmods.dev/skills/pincerhq/pincer/memory-recall)
Your own site
<a href="https://agentmods.dev/skills/pincerhq/pincer/memory-recall"><img src="https://agentmods.dev/badge/skills/pincerhq/pincer/memory-recall/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.

agentmods 80×15 button for Memory recall

Your own site · 80×15
<a href="https://agentmods.dev/skills/pincerhq/pincer/memory-recall"><img src="https://agentmods.dev/badge/skills/pincerhq/pincer/memory-recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 411 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00411
Opus 5.5 $0.00022 $0.00164
Sonnet 5.5 $0.00011 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured 2mo ago against content hash a90c4f5f7024, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Memory recall 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 2mo 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.

src/pincer/skills/memory-recall/SKILL.md · 40 lines

What it actually says

Memory recall

Pincer stores per-user memories (facts, preferences, past conversation context) in a persistent backend, separate from the current chat session. Relevant memories are already retrieved automatically and injected into your system prompt as a "Relevant memories about this user" block on every turn — you usually don't need to do anything extra to use them.

When to explicitly search memory

Reach for an explicit memory search tool (if one is registered — look for memory_search or an MCP-exposed pincer_memory_search tool) when:

  • The user references something specific from the past ("what did I tell you about my allergy last month?") that may not have matched the automatic top-3 relevance injection.
  • You need more than the ~3 memories already injected into context.
  • The user asks a direct "what do you remember about me" question — search broadly rather than relying only on what's already in context.

What gets remembered

Memories are tied to a pincer_user_id (the canonical cross-channel identity) and are searched by text relevance against the current message. Each memory is a short fact or note, not a full transcript — don't expect verbatim conversation recall, expect distilled facts ("prefers metric units", "allergic to shellfish", "working on a Rust project called Foo").

If the user asks you to forget something

There is no automatic redaction — if a memory-delete capability exists in your current tool set, use it explicitly and confirm back to the user what was removed. If no such tool is available, tell the user honestly that you can't delete stored memories from this session rather than pretending to.

Changes

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.

  1. 2mo ago First seen · 40 lines · 54 tokens per session scan A a90c4f5f7024

Subscribe to this mod's changes

Memory recall is a skill published in the GitHub repository pincerhq/pincer (44 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 411 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.

Memory and context
Related

Memory recall compared with skills from other repositories

Memory recall next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Memory recallpincerhq/pincerSkill44yesterdayMITA54Claude Code, Codex
knowledge-ingestopenclaw/openclawSkill394kyesterdayMITA80Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
forgetasgeirtj/system_prompts_leaksSkill71k2d agoCC0-1.0A74Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
memoryopensquilla/opensquillaSkill7.1k6d agoApache-2.0A44Claude Code, Codex
ha-data-storesshiwenwen/hope-agentSkill1.9kyesterdayMITA115Claude Code, Codex