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 agentmods add skills/hrithik-gavankar/brainstack/engineer-brainnpx skills add Hrithik-Gavankar/brainstack --skill engineer-braingit clone --depth 1 https://github.com/Hrithik-Gavankar/brainstackWhat 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 | $0.00133 | $0.03816 |
| Opus 5 | $0.00067 | $0.01908 |
| Sonnet 5 | $0.00027 | $0.00763 |
| Haiku 4.5 | $0.00013 | $0.00382 |
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.
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
- Git history across repos in your workspace
- GitHub activity via
gh(authored PRs, reviews, releases/tags) — often more accurate than local commits alone - BRAIN.md at
${SKILL_DIR}/BRAIN.md(the living document) - Agent transcripts in the Cursor projects folder (demos, skill work, non-commit tasks)
- Jira / Linear / project tracker via MCP or integration skill (if available)
Critical: Standup-relevant work is frequently not in authored git commits.
Reviews, releases, demos, office-hours/meetup prep, cross-team notifications, and
design-feedback incorporation must be pulled from GitHub/Jira/transcripts/BRAIN —
not inferred from git log --author alone.
Commands
Parse the user's request to determine which command to run:
sync (daily standup helper)
Generate today's standup notes.
Scope: Current team and current role only.
Only include work from team repos / team activities in this workspace.
Never reference past roles or personal/side projects — this is for your
team's standup thread. Repos listed in PERSONAL_REPOS inside scan.sh
are excluded from team standup scope.
Schedule: Workdays only (Monday–Friday). If today is Monday, "yesterday" means last Friday. If today is a weekend, skip — standups don't happen on weekends.
- Determine the lookback window based on the day of week:
- Monday: Friday only — ignore Saturday and Sunday; 3-day scan for data,
filter standup bullets and
ghto Friday-dated activity only - Tuesday–Friday: scan last 1 day
- Saturday/Sunday: tell the user "No standup today — it's the weekend." and stop.
bash "${SKILL_DIR}/scripts/scan.sh" "$HOME/path/to/workspace" [1 or 3] - Monday: Friday only — ignore Saturday and Sunday; 3-day scan for data,
filter standup bullets and
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.
- 2d ago First seen · 395 lines · 133 tokens per session scan A 0e1ff5c3a2d7
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.
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.
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.
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…
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.
skill-resume
Pick up where you left off from a previous session — use after context resets, compaction, or new conversations.
skill-status
Show where you are in the workflow and what to do next — use for progress checks and orientation.