recall

An agent skill by cursor, from cursor/plugins. Tags: analysis, documentation, history, research, workflow.

What it does

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add cursor/plugins --skill recall

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/pstack/skills/recall ~/.claude/skills/recall

Safety box score

Grade C, moderate risk: 26 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a context-recall workflow: it reads local Cursor chat transcripts, checks git/gh state, and may query connected issue/incident systems to rebuild a work brief. The main risks are broad access to local chat history outside the project tree and outbound lookups to remote services for PRs, tickets, and incidents.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It directs the agent to run verification commands like `git` and `gh` and to spawn subagents, but it does not ship arbitrary scripts or code execution payloads.
Network access	2 (moderate)	It explicitly sweeps remote records across "source control, the issue tracker, chat and issue channels, long-form docs, and error tracking" and tells the agent to check PRs/tickets with `gh`.
Filesystem reach	2 (moderate)	It reads chat transcripts from `~/.cursor/projects/<slug>/agent-transcripts/<uuid>/<uuid>.jsonl`, which is outside the project directory and can expose other local workspaces' history.
Secrets & credentials	1 (low)	The skill mines chat history and shared records for context, which may include pasted secrets or incident details, but it does not directly access keychains, `.env` files, or credential stores.
Privilege & persistence	0 (none)	There is no request for sudo, global installs, services, shell startup changes, or other privilege escalation.
Instruction hijack surface	0 (none)	The file does not instruct the agent to ignore safeguards or follow untrusted remote instructions; it instead says to sanitize private context before public output.
Irreversible actions	1 (low)	Its purpose is read-only summarization and verification; it does not publish, deploy, pay, or otherwise change external systems.
Transparency	0 (none)	There are no binaries, minified assets, decoded-at-runtime blobs, or unpinned installers in the skill file.

Before installing

Confirm you are comfortable with the agent reading `~/.cursor/projects/.../agent-transcripts/...jsonl` in your home directory.
Make sure `gh` access to the relevant repos/issues is intended for this workspace.
Test it first on a non-sensitive project if your chat history or incident records may contain secrets.
Review whether cross-project transcript access is acceptable, even though the skill says not to read another project's transcripts without being asked.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: cursor/plugins (all skills from this repository)
Path: pstack/skills/recall/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
show-me-your-work — Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).
swarm — Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
verify-this — Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED.
workflow-from-chats — Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs.
spec-to-code-compliance — Check code against the documentation that specifies it - which requirements hold, which the code contradicts, which are absent.