engineer-brain

A self-updating record of an engineer's work, skills, habits, progress gaps, and current focus. It combines Git, GitHub, BRAIN.md, agent transcripts, and—when available—project-tracker information.

In plain words
What is it for?
Preparing daily standups, answering what you worked on, tracking progress, identifying growth areas, and creating quarterly review content for your current team and role.
Why use it?
It captures important work that may not appear in your own commits, such as code reviews, releases, demos, and design feedback.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/hrithik-gavankar/brainstack/engineer-brain
Any agent
npx skills add Hrithik-Gavankar/brainstack --skill engineer-brain
Clone the repo
git clone --depth 1 https://github.com/Hrithik-Gavankar/brainstack

Made for: Claude Code, Codex.

Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00133 $0.03816
Opus 5 $0.00067 $0.01908
Sonnet 5 $0.00027 $0.00763
Haiku 4.5 $0.00013 $0.00382

Measured 2d ago against content hash 0e1ff5c3a2d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineer-brain 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 2d 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.

platforms/cursor/skills/engineer-brain/SKILL.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

engineer-brain — Self-Updating Engineering Context

A living system that learns how you work, what you focus on, where you're growing, and where you should push further. Produces actionable output for daily syncs and quarterly reviews.

Data Sources

  1. Git history across repos in your workspace
  2. GitHub activity via gh (authored PRs, reviews, releases/tags) — often more accurate than local commits alone
  3. BRAIN.md at ${SKILL_DIR}/BRAIN.md (the living document)
  4. Agent transcripts in the Cursor projects folder (demos, skill work, non-commit tasks)
  5. Jira / Linear / project tracker via MCP or integration skill (if available)

Critical: Standup-relevant work is frequently not in authored git commits. Reviews, releases, demos, office-hours/meetup prep, cross-team notifications, and design-feedback incorporation must be pulled from GitHub/Jira/transcripts/BRAIN — not inferred from git log --author alone.


Commands

Parse the user's request to determine which command to run:

sync (daily standup helper)

Generate today's standup notes.

Scope: Current team and current role only. Only include work from team repos / team activities in this workspace. Never reference past roles or personal/side projects — this is for your team's standup thread. Repos listed in PERSONAL_REPOS inside scan.sh are excluded from team standup scope.

Schedule: Workdays only (Monday–Friday). If today is Monday, "yesterday" means last Friday. If today is a weekend, skip — standups don't happen on weekends.

  1. Determine the lookback window based on the day of week:
    • Monday: Friday only — ignore Saturday and Sunday; 3-day scan for data, filter standup bullets and gh to Friday-dated activity only
    • Tuesday–Friday: scan last 1 day
    • Saturday/Sunday: tell the user "No standup today — it's the weekend." and stop.
    bash "${SKILL_DIR}/scripts/scan.sh" "$HOME/path/to/workspace" [1 or 3]
    

Read the full file on GitHub · 395 lines

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. 2d ago First seen · 395 lines · 133 tokens per session scan A 0e1ff5c3a2d7

Subscribe to this mod's changes

engineer-brain is a skill published in the GitHub repository Hrithik-Gavankar/brainstack (5 stars, last pushed 13d ago), licensed MIT. It adds 133 tokens to every session and 3,816 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

career-ops

AI job search command center -- evaluate offers, generate CVs, scan portals, track applications. Use when the user pastes a job URL or JD, asks to scan portals, generate a CV/PDF, track applications, prepare for interviews, draft outreach/emails, or run any career-ops mode.

santifer/career-ops · 66 tokens

scrape

Finds new job postings matching your profile via installed portal-search CLIs (LinkedIn, local job boards, and any skills added with /add-portal). Deduplicates across runs. Triggers on: job scrape, find jobs, search jobs, new jobs, job search, scrape jobs, /scrape.

MadsLorentzen/ai-job-search · 67 tokens

jobdanmark-search

Make sure to use this skill whenever the user mentions anything related to Danish job listings, job search in Denmark, finding work in Denmark, or job vacancies on Jobdanmark — even if they don't explicitly mention jobdanmark.dk. Also invoke this skill for questions about specific Danish job categories…

MadsLorentzen/ai-job-search · 299 tokens

job-application-assistant

Assists with job applications: evaluating job postings, tailoring CVs, writing cover letters, and preparing for interviews. Triggers on keywords like: job posting, job application, CV, cover letter, resume, interview prep, job fit, career, application, apply, ansøgning, stilling.

MadsLorentzen/ai-job-search · 67 tokens

skill-resume

Pick up where you left off from a previous session — use after context resets, compaction, or new conversations.

nyldn/claude-octopus · 26 tokens

skill-status

Show where you are in the workflow and what to do next — use for progress checks and orientation.

nyldn/claude-octopus · 22 tokens