How do I install the Hforge Recursive Investigate skill?

Run npx skillmds@latest add ldilov/hforge-recursive-investigate-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Hforge Recursive Investigate safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Hforge Recursive Investigate?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Hforge Recursive Investigate free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Hforge Recursive Investigate?

ldilov (@ldilov) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Hforge Recursive Investigate by ldilov

Name: Hforge Recursive Investigate
Author: ldilov

Hforge Recursive Investigate

Auto-discoverable wrapper for the Harness Forge recursive-investigate workflow. Use when a task is ambiguous, cross-module, investigation-heavy, or likely to benefit from Typed RLM, bounded subcalls, and durable recursive artifacts.

ldilov a924f2e 2.0 KB Updated Sep 17, 2026

File contents

User Input

$ARGUMENTS

You must consider the user input before proceeding.

Goal

Use Harness Forge recursive mode as an explicit investigation operating layer for hard tasks, preferring Typed RLM first and only falling back to bounded structured analysis when necessary.

Execution

Treat the text after /hforge-recursive-investigate as the investigation objective or task focus.
Inspect .hforge/agent-manifest.json, .hforge/runtime/index.json, .hforge/runtime/recursive/language-capabilities.json, .hforge/runtime/recursive/runtime-inventory.json, and .hforge/runtime/recursive/escalation-heuristics.json first when present.
Run hforge recursive capabilities --root . --json before claiming recursive support for the active language or target.
Run hforge recursive runtimes --root . --json before assuming Python or PowerShell code-cell availability.
Use hforge recursive provision-runtime <python|powershell> --root . --json only when a workspace-managed runtime alias is genuinely useful.
Create or inspect a session with hforge recursive plan "<objective>" --task-id <taskId> --root . --json or hforge recursive inspect <sessionId> --root . --json.
Prefer Typed RLM through hforge recursive execute <sessionId> --file <bundle.json> --root . --json or --stdin.
Use hforge recursive run <sessionId> --file <snippet> or --stdin only when one bounded structured-analysis step is the right tool.
Inspect durable artifacts with hforge recursive iterations, subcalls, cells, promotions, meta-ops, score, and replay.
Reuse the recursive artifacts in your summary instead of re-scanning the whole repo.
Keep product code unchanged unless the user explicitly asks for edits.

---name: hforge-recursive-investigate-2description: Auto-discoverable wrapper for the Harness Forge recursive-investigate workflow. Use when a task is ambiguous, cross-module, investigation-heavy, or likely to benefit from Typed RLM, bounded subcalls, and durable recursive artifacts.---## User Input```text$ARGUMENTS```You must consider the user input before proceeding.## GoalUse Harness Forge recursive mode as an explicit investigation operating layerfor hard tasks, preferring Typed RLM first and only falling back to boundedstructured analysis when necessary.## Execution1. Treat the text after `/hforge-recursive-investigate` as the investigation objective or task focus.2. Inspect `.hforge/agent-manifest.json`, `.hforge/runtime/index.json`, `.hforge/runtime/recursive/language-capabilities.json`, `.hforge/runtime/recursive/runtime-inventory.json`, and `.hforge/runtime/recursive/escalation-heuristics.json` first when present.3. Run `hforge recursive capabilities --root . --json` before claiming recursive support for the active language or target.4. Run `hforge recursive runtimes --root . --json` before assuming Python or PowerShell code-cell availability.5. Use `hforge recursive provision-runtime <python|powershell> --root . --json` only when a workspace-managed runtime alias is genuinely useful.6. Create or inspect a session with `hforge recursive plan "<objective>" --task-id <taskId> --root . --json` or `hforge recursive inspect <sessionId> --root . --json`.7. Prefer Typed RLM through `hforge recursive execute <sessionId> --file <bundle.json> --root . --json` or `--stdin`.8. Use `hforge recursive run <sessionId> --file <snippet>` or `--stdin` only when one bounded structured-analysis step is the right tool.9. Inspect durable artifacts with `hforge recursive iterations`, `subcalls`, `cells`, `promotions`, `meta-ops`, `score`, and `replay`.10. Reuse the recursive artifacts in your summary instead of re-scanning the whole repo.11. Keep product code unchanged unless the user explicitly asks for edits.

Frequently asked questions