AGENTS.md@packages/senpi-task/src/tools/taskA

AGENTS.md@packages/senpi-task/src/tools/task from code-yeongyu/oh-my-openagent is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add code-yeongyu/oh-my-openagent/packages/senpi-task/src/tools/task/AGENTS.md@git:20261010.03c01fb

Pins git:20261010.03c01fb in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
code-yeongyu/oh-my-openagent
Path
packages/senpi-task/src/tools/task/AGENTS.md
Versions recorded
4
Latest version
git:20261010.03c01fb, committed Oct 10, 2026
First version recorded
Aug 24, 2026
Size
3,427 bytes
Repository stars
70,763
License
a license file GitHub does not identify

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# tools/task - The `task` Tool

Single or `tasks:[...]` batch spawn of child tasks routed by category or agent. Tool contracts, plan-gated agents, and batch semantics live in the package AGENTS.md; this file maps the modules and the validation rules. 54 files, the largest tool subtree.

## Anatomy

| Path | Purpose |
|------|---------|
| `tool.ts` | `createTaskTool` / `TASK_TOOL_NAME` (`"task"`). |
| `params.ts` | TypeBox `TaskToolParams`; batches have no per-call size cap - items beyond the run limit queue in `TaskConcurrency`. Prompts MUST be English; `prompt` XOR `tasks`. |
| `argument-normalization.ts` | Batch item inheritance from top-level params; empty provider padding normalized before validation; item-level `run_in_background` mirrors survive. |
| `validation.ts` | `validateTaskTarget`, `resolveSpawnItems`, `validateBatchShape`, `resolveRunInBackground`; codes `both_targets` / `no_target` / `category_with_model` / `run_in_background_conflict`. |
| `categories.ts` / `description.ts` | Category/agent discovery and prompt description builders (plan-gated names get their own line). |
| `execute.ts` | Entry: shape validation -> item resolution -> single/batch dispatch. |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add code-yeongyu/oh-my-openagent/packages/senpi-task/src/tools/task/AGENTS.md@sha256:3b12edd305d3c8d7

The line at the top of this page pins the label git:20261010.03c01fb, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_lasrsk6jij52slwa.svg)](https://markdownregistry.com/a/art_lasrsk6jij52slwa)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Aug 24, 2026 and Oct 10, 2026, about one every 16 days.

versioncommittedcommitsizeaudit
git:20261010.03c01fb latest2026-10-10 03c01fb 3,427 BA view · diff
git:20260910.00afeac2026-09-10 00afeac 3,284 BA view · diff
git:20260903.aec32fa2026-09-03 aec32fa 3,266 BA view · diff
git:20260824.f7cdde82026-08-24 f7cdde8 2,800 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (3427 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

code-yeongyu/oh-my-openagent · 70,763 stars · license a license file GitHub does not identify · pushed 2026-11-07 · branch dev

API

GET https://markdownregistry.com/api/v1/artifacts/art_lasrsk6jij52slwa
GET https://markdownregistry.com/api/v1/resolve?ref=code-yeongyu/oh-my-openagent/packages/senpi-task/src/tools/task/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/3b12edd305d3c8d78b47ba2dfdc50bafc923245e4b3bf7f66678f4c3b685fcf5

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from code-yeongyu/oh-my-openagent

AGENTS.md@.agents AGENTS.md file
code-yeongyu/oh-my-openagent · .agents/AGENTS.md
git:20260923.2f99bd2 · audit A · 70,763 stars
codex-qa SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/codex-qa/SKILL.md · QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is…
git:20260923.2f99bd2 · audit A · 70,763 stars
get-unpublished-changes SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/get-unpublished-changes/SKILL.md · Compare HEAD with the latest published npm versions and list all unpublished changes by release layer. Triggers…
git:20260801.03121f8 · audit A · 70,763 stars
github-triage SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/github-triage/SKILL.md · Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and…
git:20260513.2146071 · audit A · 70,763 stars
hyperplan SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/hyperplan/SKILL.md · Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low…
git:20260923.573d36a · audit A · 70,763 stars
omomomo SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/omomomo/SKILL.md · Easter egg command - about oh-my-opencode. Triggers: omomomo, about, easter egg.
git:20260731.b3b45cd · audit A · 70,763 stars
opencode-qa SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/opencode-qa/SKILL.md · QA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve, export), prove a specific plugin…
git:20260708.0806e41 · audit B · 70,763 stars
pre-publish-review SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/pre-publish-review/SKILL.md · Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm…
git:20260904.cd0c0a3 · audit A · 70,763 stars
publish SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/publish/SKILL.md · Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only…
git:20261025.4b02a69 · audit A · 70,763 stars
remove-deadcode SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/remove-deadcode/SKILL.md · Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead…
git:20261105.ab2c2d5 · audit A · 70,763 stars
security-research SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/security-research/SKILL.md · Team Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a codebase in…
git:20260920.2a3e860 · audit A · 70,763 stars
senpi-qa SKILL.md skill
code-yeongyu/oh-my-openagent · .agents/skills/senpi-qa/SKILL.md · QA the omo Senpi adapter (packages/omo-senpi, packages/senpi-task) against the REAL senpi binary in strict isolation…
git:20260923.2f99bd2 · audit A · 70,763 stars

Every file in code-yeongyu/oh-my-openagent

Browse by kind, by grade A, or by owner.