{
 "schema_version": 1,
 "generated": "2026-10-24",
 "id": "arihantdeva-heimdall--brief-agent-with-prior-work-first-prompt",
 "repo": "ArihantDeva/heimdall",
 "repo_url": "https://github.com/ArihantDeva/heimdall",
 "repo_slug": "arihantdeva-heimdall",
 "title": "Start agent sessions with relevant prior work already loaded",
 "page_title": "How to start agent sessions with relevant prior work already loaded with Heimdall",
 "summary": "Inject past project context into a new agent session so it skips the orientation loop.",
 "who": "A developer who starts a fresh coding agent session on a project and wants it to know what was done before.",
 "problem": "A new agent session spends dozens of shell commands re-reading files it already saw last week.",
 "outcome": "The agent begins with relevant prior work in its first prompt and can answer with one kb_search call instead of many grep and ls commands.",
 "steps": [
  "`npm i -g @arihantdeva/heimdall`",
  "`heimdall init --harness claude-code`",
  "`heimdall setup`",
  "`heimdall doctor`",
  "Open a new agent session in the project folder and ask it to call kb_search on <topic> before it starts editing"
 ],
 "agent_prompt": "In the ArihantDeva/heimdall setup, start a session in <project-folder> and call kb_search on <topic> before any shell exploration. Expected output: a short list of prior work with verdicts and paths. Verify that the first useful action uses a STRONG hit or that the agent says a hit is WEAK.",
 "agents": [
  "claude-code",
  "codex",
  "cursor"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "The README names only some harnesses as wired by `heimdall init`, and the exact injection behavior for each harness is not described in detail, so test it in your own harness before relying on it.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "javascript",
 "requirements": [
  "Node.js with npm, to run `npm i -g @arihantdeva/heimdall`",
  "macOS or a Debian, Ubuntu, Fedora or Amazon Linux machine, with the build prerequisites listed in the README for the graft backend",
  "git, because llama.cpp is cloned at first build",
  "A supported agent harness: pi, Claude Code, Codex, Cursor, Windsurf, or opencode"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/arihantdeva-heimdall/brief-agent-with-prior-work-first-prompt/",
 "md": "https://dedupedai.com/use-cases/arihantdeva-heimdall/brief-agent-with-prior-work-first-prompt/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/arihantdeva-heimdall--brief-agent-with-prior-work-first-prompt.json",
 "api_version": "v1"
}