Agent skill

Previous Work

by scott-fryxell in scott-fryxell/brayness

Search past agent sessions across all three harnesses (pi, Cursor, Claude Code) when asked about earlier work.

MITAuto-check passed

Install Previous Work

skills CLI

$ npx skills add scott-fryxell/brayness --skill previous-work -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install scott-fryxell/brayness previous-work --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/scott-fryxell/brayness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/previous-work .claude/skills/previous-work && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "previous-work" agent skill from https://github.com/scott-fryxell/brayness/tree/main/skills/previous-work into .claude/skills/previous-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "previous-work", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/scott-fryxell/brayness/tree/main/skills/previous-work

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add scott-fryxell/brayness --skill previous-work -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install scott-fryxell/brayness previous-work --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/scott-fryxell/brayness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/previous-work .agents/skills/previous-work && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "previous-work" agent skill from https://github.com/scott-fryxell/brayness/tree/main/skills/previous-work into .agents/skills/previous-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "previous-work", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add scott-fryxell/brayness --skill previous-work -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install scott-fryxell/brayness previous-work --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/scott-fryxell/brayness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/previous-work .cursor/skills/previous-work && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "previous-work" agent skill from https://github.com/scott-fryxell/brayness/tree/main/skills/previous-work into .cursor/skills/previous-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "previous-work", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/scott-fryxell/brayness.git --path skills/previous-work

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add scott-fryxell/brayness --skill previous-work -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install scott-fryxell/brayness previous-work --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/scott-fryxell/brayness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/previous-work .gemini/skills/previous-work && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "previous-work" agent skill from https://github.com/scott-fryxell/brayness/tree/main/skills/previous-work into .gemini/skills/previous-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "previous-work", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install scott-fryxell/brayness previous-work

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add scott-fryxell/brayness --skill previous-work -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/scott-fryxell/brayness.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/previous-work .github/skills/previous-work && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "previous-work" agent skill from https://github.com/scott-fryxell/brayness/tree/main/skills/previous-work into .github/skills/previous-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "previous-work", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add scott-fryxell/brayness --skill previous-work -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install scott-fryxell/brayness previous-work --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/scott-fryxell/brayness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/previous-work .opencode/skills/previous-work && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "previous-work" agent skill from https://github.com/scott-fryxell/brayness/tree/main/skills/previous-work into .opencode/skills/previous-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "previous-work", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: previous-work
GitHub stars: 125
Token cost: ~926 tokens
SKILL.md length: 338 words
Files: 1
Skills in repo: 27
Repo updated: Sep 28, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Search past agent sessions across all three harnesses (pi, Cursor, Claude Code) when asked about earlier work.

The user asks what did we do about X
SKILL.md covers Ranked recall first, Where sessions live, How to search and Ground rules
Calls rg
Did we already discuss/try/fix X

What it does

Previous Work is an agent skill from scott-fryxell/brayness. Search past agent sessions across all three harnesses (pi, Cursor, Claude Code) when asked about earlier work. Use when the user asks "what did we do about X", "did we already discuss/try/fix X", "find that earlier session", "review previous work", or when a task smells like a repeat of something already done. Knows where each tool stores its JSONL transcripts and how to search them without tripping over ignore files.

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A harness for the anxious digital mind. A safe place for creatives to keep their creative soul while exploring digital skills. The licence is MIT.

When your agent uses it

The user asks what did we do about X
Did we already discuss/try/fix X
Find that earlier session
Review previous work

Example prompts

“what did we do about X”
“did we already discuss/try/fix X”
“find that earlier session”
“/previous-work”

What it can do on your machine

Read from SKILL.md and the folder at commit 71f10e2. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- rg
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Previous Work loads about 926 tokens when it runs. Until then it costs about 109 tokens; SKILL.md has 338 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~109
When it runs · the whole SKILL.md, loaded when a task matches: ~926

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from scott-fryxell/brayness at commit 71f10e2, republished under its MIT licence (© scott-fryxell). 338 words, ~926 tokens.

Download SKILL.mdSave it as .claude/skills/previous-work/SKILL.md (or your agent's skills folder).

name: previous-work
description: Search past agent sessions across all three harnesses (pi, Cursor, Claude Code) when asked about earlier work. Use when the user asks "what did we do about X", "did we already discuss/try/fix X", "find that earlier session", "review previous work", or when a task smells like a repeat of something already done. Knows where each tool stores its JSONL transcripts and how to search them without tripping over ignore files.

Previous Work

Raw transcript archaeology across pi, Cursor, and Claude Code. For distilled lessons, AGENTS.local.md Learnings is already in context (memory skill) - check it first; only dig transcripts when you need what actually happened.

Ranked recall first

The remember tool (extension extensions/memory/) indexes pi's own sessions into an FTS5 store, ~4 ms a query, newest turns re-indexed automatically. Use it before rg:

remember search "firecracker lima mac" - ranked turns with snippets, dates, and the session file to reopen. Tolerates typos; the last word also matches as a prefix. An exchange is one row, so a question and its answer surface together.
rg is for raw archaeology: every occurrence, exact strings, and the Cursor and Claude Code stores, which the index does not cover.

The store is derived, never synced, and lives at .pi/agent/memory.db. If it looks empty or stale, remember action index rebuilds it (about a second for 400 sessions).

Where sessions live

Agent	Path	Shape
pi	`.pi/agent/sessions/*.jsonl`	timestamp + uuid filenames
Cursor	`~/.cursor/projects/Users-scott-Desktop-brayness/agent-transcripts/<uuid>/<uuid>.jsonl`	one dir per chat
Claude Code	`~/.claude/projects/-Users-scott-Desktop-brayness/.jsonl`	one store per cwd

Notes:

Claude fragments by working directory: work/realness sessions live in -Users-scott-Desktop-brayness-work-realness, etc. Older stores named -Users-scott-Desktop-brain* (previous harness names) hold early work.
Cursor keeps one store per opened folder under ~/.cursor/projects/; project windows like work/realness have their own.

How to search

pi sessions are hidden from rg by the repo .ignore (sessions/ pattern) - always pass --no-ignore:

bash

rg --no-ignore -li 'search term' .pi/agent/sessions/
rg -li 'search term' ~/.cursor/projects/Users-scott-Desktop-brayness/agent-transcripts/
rg -li 'search term' ~/.claude/projects/-Users-scott-Desktop-brayness*/

Then narrow inside a hit (JSONL, one message per line):

bash

rg --no-ignore -i 'term' <file> | head -5     # locate lines
ls -t <dir> | head                             # most recent first

Filenames carry the date (pi) or check file mtime (Cursor/Claude) to order by recency when the user says "yesterday" or "last week".

Ground rules

Transcripts contain secrets and personal info. Quote the minimum that answers the question, and leave it in the transcript otherwise.
Cite where the answer came from (which store, which file, the date) so the user can reopen the session.
Not found is a real answer: say which stores you searched and with what terms instead of guessing.
Durable lessons discovered while digging go to AGENTS.local.md Learnings (memory skill) so the next search is unnecessary.

Files

Just SKILL.md in skills/previous-work of scott-fryxell/brayness.

Open the folder on GitHubat commit 71f10e2

Compare with similar skills

Previous Work next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Previous Work compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Previous Work this skillscott-fryxell/brayness	125	—	~926	Automated safety check: Pass	MIT	12 days ago
Session History Searchslopus/happy	24k	—	~3.1k	Automated safety check: Pass	MIT	today
Session Handoffsickn33/agentic-awesome-skills	47k	—	~1.8k	Automated safety check: Notes	MIT	yesterday
Coding Agent Session Findercode-yeongyu/oh-my-openagent	70k	—	~2.8k	Automated safety check: Pass	Custom licence	today
Omh Harness Session Inventoryrlaope/oh-my-hermes	3.2k	—	~1.9k	Automated safety check: Pass	MIT	today
Sessionanthropics/claude-for-legal	9.6k	3 repos	~478	Automated safety check: Pass	Apache-2.0	11 days ago

Similar skills

Session History Search
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
24k GitHub stars~3.1k tokensUpdated today
Agent WorkflowsAuto-check passed
Session Handoff
sickn33/agentic-awesome-skills
A skill your agent uses when context approaches capacity, before /clear or /compact, when switching tasks, or when ending a coding session: produces a structured handoff artifact for the next session.
47k GitHub stars~1.8k tokensUpdated yesterday
Agent WorkflowsAuto-check: notes
Coding Agent Session Finder
code-yeongyu/oh-my-openagent
Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.
70k GitHub stars~2.8k tokensUpdated today
Agent WorkflowsAuto-check passed
Omh Harness Session Inventory
rlaope/oh-my-hermes
[omh] Lost track of agent sessions and worktrees: normalize Codex, Claude Code, Hermes, OpenCode, Cursor, MCP host, worktree, and wrapper session metadata into one drift-aware inventory.
3.2k GitHub stars~1.9k tokensUpdated today
DevelopmentAuto-check passed
Session
anthropics/claude-for-legal
Official
Run a focused N-question study session on a subject — MBE, essay, or flashcards.
9.6k GitHub starsUsed in 3 repos~478 tokens
EducationAuto-check passed
Eval Harness
affaan-m/ECC
Eval-driven development (EDD) framework for AI coding sessions — define capability and regression evals before coding, grade with code-based, model-based, rule, or human graders, and track pass@k…
276k GitHub stars~2.2k tokensUpdated today
AI & LLM EngineeringAuto-check passed

More from scott-fryxell/brayness

All 27 skills in this repo

Logo Finder
scott-fryxell/brayness
Find and install brand SVG logos via SVGL (https://svgl.app/) and Wikimedia Commons fallbacks into any project's static asset folder.
125 GitHub stars~1.1k tokensUpdated 12 days ago
Auto-check passed
Test Coverage
scott-fryxell/brayness
Write Vitest specs for Vue 3 JavaScript (Vite Plus, happy-dom, @vue/test-utils) and analyze V8 coverage + Fallow health to prioritize test-first refactors.
125 GitHub stars~1.6k tokensUpdated 12 days ago
Auto-check passed
Flexible Visual System
scott-fryxell/brayness
Derive a project's visual rules from its existing tokens, palette, type scale, logo, and icons (Intake), then generate raw SVG vector graphics from those rules as a small composable set (module…
125 GitHub stars~1.9k tokensUpdated 12 days ago
Auto-check passed
Hyperframes
scott-fryxell/brayness
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML.
125 GitHub stars~3.2k tokensUpdated 12 days ago
Auto-check passed
Motion Systems
scott-fryxell/brayness
A skill your agent uses when designing or implementing motion for web interfaces, including CSS transitions and keyframes, linear() easing design, transform strategy (translate/rotate vs…
125 GitHub stars~1.7k tokensUpdated 12 days ago
Auto-check passed
Vue Inspect
scott-fryxell/brayness
Inspect live Vue 3 component state via agent-browser eval - no Devtools extension, no console.log.
125 GitHub stars~779 tokensUpdated 12 days ago
Auto-check passed

Questions about Previous Work

What does Previous Work do?

Search past agent sessions across all three harnesses (pi, Cursor, Claude Code) when asked about earlier work. Previous Work is an agent skill from scott-fryxell/brayness. Search past agent sessions across all three harnesses (pi, Cursor, Claude Code) when asked about earlier work.

When should I use Previous Work?

Previous Work fits situations like: the user asks what did we do about X; did we already discuss/try/fix X; find that earlier session; review previous work.

How do I install Previous Work in Claude Code?

Run `npx skills add scott-fryxell/brayness --skill previous-work -a claude-code`. Or copy the skill folder (skills/previous-work in scott-fryxell/brayness) into .claude/skills/previous-work in your project. Claude Code loads it when a task matches its description.

How do I install Previous Work in Codex?

Run `npx skills add scott-fryxell/brayness --skill previous-work -a codex`. Or copy the skill folder (skills/previous-work in scott-fryxell/brayness) into .agents/skills/previous-work in your project. Codex loads it when a task matches its description.

Can I use Previous Work in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add scott-fryxell/brayness --skill previous-work -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/previous-work, .gemini/skills/previous-work, .github/skills/previous-work and .opencode/skills/previous-work in your project.

What does Previous Work need to run?

Going by SKILL.md and its folder, Previous Work needs the command-line tools its instructions call (rg).

Does Previous Work access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Previous Work safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Previous Work use?

Previous Work is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Previous Work use?

About 926 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Previous Work?

Skills that share tags, products or a category with Previous Work: Session History Search (slopus/happy, 24k stars), Session Handoff (sickn33/agentic-awesome-skills, 47k stars), Coding Agent Session Finder (code-yeongyu/oh-my-openagent, 70k stars) and Omh Harness Session Inventory (rlaope/oh-my-hermes, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Previous Work?

scott-fryxell (a GitHub user) maintains it in scott-fryxell/brayness, which has 125 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on September 28, 2026.

Source: scott-fryxell/brayness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Previous Work

Facts

At a glance

What it does

When your agent uses it

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Previous Work

Ranked recall first

Where sessions live

How to search

Ground rules

Files

Compare with similar skills

Similar skills

More from scott-fryxell/brayness

Questions about Previous Work