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 scott-fryxell/brayness --skill previous-workgit clone --depth 1 https://github.com/scott-fryxell/braynessWrote 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/scott-fryxell/brayness/previous-work)<a href="https://agentmods.dev/skills/scott-fryxell/brayness/previous-work"><img src="https://agentmods.dev/badge/skills/scott-fryxell/brayness/previous-work/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/scott-fryxell/brayness/previous-work"><img src="https://agentmods.dev/badge/skills/scott-fryxell/brayness/previous-work.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00096 | $0.00654 |
| Opus 5 | $0.00048 | $0.00327 |
| Sonnet 5 | $0.00019 | $0.00131 |
| Haiku 4.5 | $0.00010 | $0.00065 |
Grade A, and why
previous-work 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 10d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
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/realnesssessions 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 likework/realnesshave their own.
How to search
pi sessions are hidden from rg by the repo .ignore (sessions/ pattern) -
always pass --no-ignore:
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):
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.mdLearnings (memoryskill) so the next search is unnecessary.
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.
- 10d ago First seen · 60 lines · 96 tokens per session scan A 3a3d7c786395
previous-work is a skill published in the GitHub repository scott-fryxell/brayness (120 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 654 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.