Agent skill

Agent Workflow

by getopenpost in getopenpost/openpost

Coordinate substantial OpenPost features, refactors, or multi-ticket work.

AGPL-3.0Auto-check passedDevelopment

Install Agent Workflow

skills CLI
$ npx skills add getopenpost/openpost --skill agent-workflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install getopenpost/openpost agent-workflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/getopenpost/openpost.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agent-workflow .claude/skills/agent-workflow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-workflow
GitHub stars
653
Token cost
~811 tokens
SKILL.md length
412 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Coordinate substantial OpenPost features, refactors, or multi-ticket work.

  • Works in 5 steps: Establish scope. Inspect the worktree,… → Record substantial work. Create or… → Implement through the owner. Work on an… → …
  • Module boundaries
  • Calls bun
  • Dependencies need to be recorded for implementation

What it does

Agent Workflow is an agent skill from getopenpost/openpost. Coordinate substantial OpenPost features, refactors, or multi-ticket work. Use when scope, module boundaries, or dependencies need to be recorded for implementation. Small, explicit changes go directly to implementation and scoped verification.

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Refactoring. The repository describes itself as: Create, adapt, schedule, and track social posts. Open-source, hosted or self-hosted. The licence is AGPL-3.0.

When your agent uses it

  • Module boundaries
  • Dependencies need to be recorded for implementation

Example prompts

  • “/agent-workflow”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Establish scope. Inspect the worktree, docs/agents/repository-map.md, and the owning code. Recall relevant Hindsight decisions and verify…
  2. Record substantial work. Create or update the internal Vikunja task with the outcome, acceptance criteria, exclusions, affected…
  3. Implement through the owner. Work on an unblocked slice. Keep relevant context and resume in the current task unless a separate context is…
  4. Review and verify. Review the candidate against the request and repository standards. Use the available code-review skill for substantial…
  5. Deliver. Follow AGENTS.md for changelogs, commits, pushes, and production approval. Record commands and outcomes in the Vikunja task…

What it can do on your machine

Read from SKILL.md and the folder at commit ed8ad44. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bun

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Workflow loads about 811 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 412 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~811

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from getopenpost/openpost at commit ed8ad44, republished under its AGPL-3.0 licence (© getopenpost). 412 words, ~811 tokens.

Download SKILL.mdSave it as .claude/skills/agent-workflow/SKILL.md (or your agent's skills folder).
name
agent-workflow
description
Coordinate substantial OpenPost features, refactors, or multi-ticket work. Use when scope, module boundaries, or dependencies need to be recorded for implementation. Small, explicit changes go directly to implementation and scoped verification.

OpenPost Agent Workflow

Follow the user's authorized scope through implementation and verification. Use the branches below only when the task needs them. Approval requirements live in AGENTS.md; routine planning and test placement do not add approval gates.

  1. Establish scope. Inspect the worktree, docs/agents/repository-map.md, and the owning code. Recall relevant Hindsight decisions and verify them against current sources. Read the matching Vikunja task when one exists. Continue when the requested outcome, affected surfaces, and verification boundary are clear. Ask only about unresolved choices that change the outcome, compatibility, or authorization. Use grilling only for a requested design interview.
  2. Record substantial work. Create or update the internal Vikunja task with the outcome, acceptance criteria, exclusions, affected interfaces, and verification. Record migrations and rollback needs when applicable. Split only work that needs independent execution, and record real blocking dependencies. Existing user authorization covers routine specification and ticketing; seek input on new product or compatibility decisions. Use available codebase-design guidance when a module boundary is unsettled.
  3. Implement through the owner. Work on an unblocked slice. Keep relevant context and resume in the current task unless a separate context is needed. Follow the repository's regression-test contract, choosing the public boundary from acceptance criteria and existing tests. Run focused checks after meaningful changes. Persistence and migration changes need evidence from a clean database or equivalent fresh state.
  4. Review and verify. Review the candidate against the request and repository standards. Use the available code-review skill for substantial changes or an explicit review request; review small changes locally. Fix supported findings, then check the affected behavior. Complete the scoped root gates and exercise the user-visible path where applicable. Repeat checks only for new edits, failures, or unresolved risks.
  5. Deliver. Follow AGENTS.md for changelogs, commits, pushes, and production approval. Record commands and outcomes in the Vikunja task. Leave unrelated findings as separate tasks. Report the result and any remaining blocker. Hand off only when another context or person must continue unfinished work.
Show full SKILL.md (84 more words)Show less

Skills supplied by the agent environment may live outside this checkout. Read their actual instructions before use; this workflow does not assume a specific review protocol or require local copies of global skills. If a context service is unavailable, report the limitation and continue work that current code and the user request establish. Keep internal task state in Vikunja.

Run bun run check -- agents when changing this workflow or its checker. docs/agents/triage-labels.md maps public GitHub intake labels; it does not configure private Vikunja work.

© getopenpost, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/agent-workflow of getopenpost/openpost.

Open the folder on GitHubat commit ed8ad44

Compare with similar skills

Agent Workflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Workflow this skillgetopenpost/openpost653—~811Automated safety check: PassAGPL-3.0
Migrate Core Code to Submodulestinyhumansai/openhuman41k—~2.6kAutomated safety check: PassGPL-3.0
Filescope MCPadmica/FileScopeMCP302—~1.7kAutomated safety check: PassProprietary
Gograph Go Repository Intelligenceozgurcd/gograph227—~4.8kAutomated safety check: NotesMIT
Auto DevflowHuangPuStar/FenixAgent552—~3kAutomated safety check: PassApache-2.0
Skill Writingmillionco/expect3.6k—~1.8kAutomated safety check: PassCustom licence

Similar skills

  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    41k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Filescope MCP

    admica/FileScopeMCP

    Codebase intelligence via FileScopeMCP — symbol lookup, dependency mapping, importance ranking, and semantic search.

    302 GitHub stars~1.7k tokensUpdated 4 mo ago
    DevelopmentAuto-check passed
  • Gives an agent working in a Go codebase a structural view through a local MCP server: call graphs, blast-radius and impact analysis, and bounded first-call exploration.

    227 GitHub stars~4.8k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Auto Devflow

    HuangPuStar/FenixAgent

    A skill your agent uses when starting an issue, bugfix, feature, or refactor that should be driven by multiple coordinated subagents: explore → plan → code → review, with the main agent acting as…

    552 GitHub stars~3k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Skill Writing

    millionco/expect

    Write and improve agent skills (SKILL.md files). An agent skill from millionco/expect.

    3.6k GitHub stars~1.8k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed
  • Ss Cpp Modern

    Serial-Studio/Serial-Studio

    Modern C++20 authoring guidance for Serial Studio (Qt 6.11, C++20): concepts, ranges, move/RAII, std smart pointers, constexpr, lock-free SPSC atomics.

    7.2k GitHub stars~1.6k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from getopenpost/openpost

  • Openpost CLI

    getopenpost/openpost

    Operate a running OpenPost instance through the openpost CLI.

    653 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Cuelume

    getopenpost/openpost

    Add or audit OpenPost interaction sounds with Cuelume. An agent skill from getopenpost/openpost.

    653 GitHub stars~620 tokensUpdated yesterday
    Auto-check passed
  • Huma

    getopenpost/openpost

    Huma - Go REST/RPC API Framework. An agent skill from getopenpost/openpost.

    653 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Openapi Typescript

    getopenpost/openpost

    Type-safe OpenAPI consumption in TypeScript using openapi-typescript and openapi-fetch.

    653 GitHub stars~887 tokensUpdated yesterday
    Auto-check passed
  • Openpost SEO

    getopenpost/openpost

    Audit OpenPost marketing and documentation SEO with the pinned claude-seo toolkit.

    653 GitHub stars~766 tokensUpdated yesterday
    Auto-check passed
  • UX Consistency

    getopenpost/openpost

    OpenPost acceptance bar for frontend UI and copy changes. An agent skill from getopenpost/openpost.

    653 GitHub stars~680 tokensUpdated yesterday
    Auto-check passed

Questions about Agent Workflow

What does Agent Workflow do?

Coordinate substantial OpenPost features, refactors, or multi-ticket work. Agent Workflow is an agent skill from getopenpost/openpost. Coordinate substantial OpenPost features, refactors, or multi-ticket work.

When should I use Agent Workflow?

Agent Workflow fits situations like: module boundaries; dependencies need to be recorded for implementation.

How do I install Agent Workflow in Claude Code?

Run `npx skills add getopenpost/openpost --skill agent-workflow -a claude-code`. Or copy the skill folder (.agents/skills/agent-workflow in getopenpost/openpost) into .claude/skills/agent-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Agent Workflow in Codex?

Run `npx skills add getopenpost/openpost --skill agent-workflow -a codex`. Or copy the skill folder (.agents/skills/agent-workflow in getopenpost/openpost) into .agents/skills/agent-workflow in your project. Codex loads it when a task matches its description.

Can I use Agent Workflow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add getopenpost/openpost --skill agent-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-workflow, .gemini/skills/agent-workflow, .github/skills/agent-workflow and .opencode/skills/agent-workflow in your project.

What does Agent Workflow need to run?

Going by SKILL.md and its folder, Agent Workflow needs the command-line tools its instructions call (bun).

Does Agent Workflow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Workflow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Workflow use?

Agent Workflow is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Workflow use?

About 811 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Workflow?

Skills that share tags, products or a category with Agent Workflow: Migrate Core Code to Submodules (tinyhumansai/openhuman, 41k stars), Filescope MCP (admica/FileScopeMCP, 302 stars), Gograph Go Repository Intelligence (ozgurcd/gograph, 227 stars) and Auto Devflow (HuangPuStar/FenixAgent, 552 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Workflow?

getopenpost (a GitHub organization) maintains it in getopenpost/openpost, which has 653 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 6, 2026.

Source: getopenpost/openpost on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.