start-work SKILL.md skillA

start-work from utsavbalar1231/oh-my-claudeagent is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add utsavbalar1231/oh-my-claudeagent/start-work@git:20261015.c0bb9cf

Pins git:20261015.c0bb9cf in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
utsavbalar1231/oh-my-claudeagent
Path
skills/start-work/SKILL.md
Versions recorded
5
Latest version
git:20261015.c0bb9cf, committed Oct 15, 2026
First version recorded
Oct 6, 2026
Size
27,435 bytes
Repository stars
3
License
MIT

Start a work session from a planner-generated plan.

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

Call `health_check` first, loading it and `boulder_write` if needed: `ToolSearch({query: "select:mcp__plugin_oh-my-claudeagent_omca__health_check,mcp__plugin_oh-my-claudeagent_omca__boulder_write", max_results: 2})`. Proceed only when `runtime` is `ok`; otherwise repeat `runtime_reason` to the user, tell them to run `/oh-my-claudeagent:omca-setup`, and stop. If the tool is still missing, say OMCA's server is not connected and stop.

# Plan execution mode: start-work

This command runs in the main session at depth 0. The `Agent` tool is available,
so orchestration is real: parallel fan-out to `executor`, specialist escalation
via `build-fixer`/`explorer`/`researcher` as needed.

The platform's native Workflow tool is not a substitute for this command. A workflow run
is driven by the platform's own runtime, so its agents never call `evidence_log`, never
bind a plan, and OMCA's plan gates never see them. That makes it a separate lane, not a
replacement for plan execution here.

## Refusal clause

This command body runs in the main session at depth 0. If the `Agent` tool is not in
your tool list (a `--tools`, `--disallowedTools`, or deny-rule restriction removed it),
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add utsavbalar1231/oh-my-claudeagent/start-work@sha256:d3282d2594be3abe

The line at the top of this page pins the label git:20261015.c0bb9cf, 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_mxulsnsojedogzkr.svg)](https://markdownregistry.com/a/art_mxulsnsojedogzkr)

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

Versions

The registry has recorded 5 versions of this file, between Oct 6, 2026 and Oct 15, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261015.c0bb9cf latest2026-10-15 c0bb9cf 27,435 BA view · diff
git:20261014.0cfa3842026-10-14 0cfa384 27,431 BA view · diff
git:20261014.6cafef82026-10-14 6cafef8 27,057 BA view · diff
git:20261006.6b1d9b62026-10-06 6b1d9b6 26,865 BA view · diff
git:20261006.526f3232026-10-06 526f323 26,983 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (27435 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

utsavbalar1231/oh-my-claudeagent · 3 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_mxulsnsojedogzkr
GET https://markdownregistry.com/api/v1/resolve?ref=utsavbalar1231/oh-my-claudeagent/start-work
GET https://markdownregistry.com/api/v1/blob/d3282d2594be3abe79da36c1036c74405eb1f8b44011f75c00c995a85316cac4

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: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from utsavbalar1231/oh-my-claudeagent

AGENTS.md AGENTS.md file
utsavbalar1231/oh-my-claudeagent · AGENTS.md
git:20261101.b22e828 · audit A · 3 stars
AGENTS.md@hooks AGENTS.md file
utsavbalar1231/oh-my-claudeagent · hooks/AGENTS.md
git:20261101.2ada52d · audit A · 3 stars
AGENTS.md@opencode AGENTS.md file
utsavbalar1231/oh-my-claudeagent · opencode/AGENTS.md
git:20261016.2c892bc · audit A · 3 stars
AGENTS.md@scripts AGENTS.md file
utsavbalar1231/oh-my-claudeagent · scripts/AGENTS.md
git:20261016.a891e46 · audit A · 3 stars
AGENTS.md@servers AGENTS.md file
utsavbalar1231/oh-my-claudeagent · servers/AGENTS.md
git:20261016.a2712e8 · audit A · 3 stars
AGENTS.md@skills AGENTS.md file
utsavbalar1231/oh-my-claudeagent · skills/AGENTS.md
git:20261006.526f323 · audit A · 3 stars
analyzer SKILL.md skill
utsavbalar1231/oh-my-claudeagent · skills/analyzer/SKILL.md · Pre-planning analysis via the analyzer. Catches gaps, identifies risks, surfaces hidden requirements.
git:20261015.c0bb9cf · audit A · 3 stars
build-fixer SKILL.md skill
utsavbalar1231/oh-my-claudeagent · skills/build-fixer/SKILL.md · Use when a build, type check or dependency install fails, or the user pastes a compiler error or says "fix build". Runs…
git:20261015.c0bb9cf · audit A · 3 stars
consolidate-memory SKILL.md skill
utsavbalar1231/oh-my-claudeagent · skills/consolidate-memory/SKILL.md · Use when a plan finishes or agent memories have piled up. Merges agent project memories and notepad learnings into the…
git:20261003.db01775 · audit A · 3 stars
debugging SKILL.md skill
utsavbalar1231/oh-my-claudeagent · skills/debugging/SKILL.md · Use for runtime bugs: crashes, wrong output, intermittent or silent failures, flaky tests, code that works locally but…
git:20261015.c0bb9cf · audit A · 3 stars
git-master SKILL.md skill
utsavbalar1231/oh-my-claudeagent · skills/git-master/SKILL.md · MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). Triggers…
git:20261015.c0bb9cf · audit A · 3 stars
github-triage SKILL.md skill
utsavbalar1231/oh-my-claudeagent · skills/github-triage/SKILL.md · Use to triage open GitHub issues and PRs in parallel, read-only, one executor per item ("triage issues", "review open…
git:20261022.ad189a8 · audit A · 3 stars

Every file in utsavbalar1231/oh-my-claudeagent

Other files named start-work

start-work SKILL.md skill
wjgoarxiv/litclaude · plugins/litclaude/skills/start-work/SKILL.md · Execute a checked plan file with LitClaude Boulder state, top-level checkbox discipline, goal/workflow/worktree…
git:20261029.dc73a50 · audit A · 5 stars

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