agentic-workflow-init

agentic-workflow-init is a skill for Claude Code, Codex from mperkhou/career-agent-workbench. It costs 59 tokens per session (411 once invoked), scanned A, original, MIT.

A setup process for starting a committed agentic workflow plan before implementation. It creates the plan, version and changelog entries, and tracking state for the workflow.

In plain words
What is it for?
Checking repository readiness, creating a versioned workflow plan, initializing its ignored tracker, binding the tracker to the plan, and producing a kickoff prompt.
Why use it?
It gives a new multi-step coding task an agreed scope and a recorded starting point before code changes begin.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mperkhou/career-agent-workbench/agentic-workflow-init
Any agent
npx skills add mperkhou/career-agent-workbench --skill agentic-workflow-init
Clone the repo
git clone --depth 1 https://github.com/mperkhou/career-agent-workbench

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agentic-workflow-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/mperkhou/career-agent-workbench/agentic-workflow-init.svg)](https://agentmods.dev/skills/mperkhou/career-agent-workbench/agentic-workflow-init)
Your own site
<a href="https://agentmods.dev/skills/mperkhou/career-agent-workbench/agentic-workflow-init"><img src="https://agentmods.dev/badge/skills/mperkhou/career-agent-workbench/agentic-workflow-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 411 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00411
Opus 5 $0.00030 $0.00205
Sonnet 5 $0.00012 $0.00082
Haiku 4.5 $0.00006 $0.00041

Measured 4d ago against content hash 18d1c3537594, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agentic-workflow-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/agentic-workflow-init/SKILL.md · 40 lines

What it actually says

Agentic Workflow Init

Follow root AGENTS.md. This skill creates control state only; it does not implement product work, mutate application rows/artifacts, push, open a PR, merge, tag, release, or contact an external system.

Bootstrap

  1. Verify the repository root, worktree, current branch, remote baseline, and operator authority.
  2. Confirm one target SemVer and create the feature branch.
  3. Create the committed canonical plan at docs/agentic-workflows/<version>-<slug>.md using the controller plan asset.
  4. Add the matching top changelog heading and bootstrap bullet.
  5. Commit the plan and changelog before implementation.
  6. Initialize ignored runtime state bound to the committed plan digest, revision, branch, bootstrap commit, current P step, and pause conditions.
  7. Return a kickoff prompt for $agentic-workflow-controller.

Use the public environment helper:

.venv/bin/python skills/agentic-workflow-controller/scripts/workflow_state.py \
  init <workflow-id> --version <X.Y.Z> --objective "<objective>" \
  --current-step P01 --branch <branch> \
  --plan-path docs/agentic-workflows/<X.Y.Z>-<slug>.md \
  --plan-revision 1 --bootstrap-commit <commit>

Runtime state belongs under ignored tmp/agentic-workflows/<workflow-id>/ and must remain a cursor/evidence log, not a competing plan. Keep sensitive or heavy evidence outside the repository tree. User authority remains required for publication, destructive work, private application mutation, and release closeout.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 40 lines · 59 tokens per session scan A 18d1c3537594

Subscribe to this mod's changes

agentic-workflow-init is a skill published in the GitHub repository mperkhou/career-agent-workbench (0 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 411 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

html-ppt-zhangzara-capsule

A year-end self-review for a product manager — the role, the outcomes, the learning, and the ask, all evidence-backed. Built as a decision-grade career deck for manager, review committee.

nexu-io/open-design · 52 tokens

enferno-dev

Development skill for Enferno Flask framework. Use when implementing features, fixing bugs, or writing code for Enferno-based applications. This includes creating models, API endpoints, Vue.js frontend components, database operations, or any development task within the Enferno ecosystem. Triggers: creating blueprints…

level09/enferno · 82 tokens

figma-use

MANDATORY prerequisite — you MUST invoke this skill BEFORE every usefigma tool call. NEVER call usefigma directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in…

Haohao-end/openagent · 114 tokens

cli-creator

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a…

Haohao-end/openagent · 82 tokens

evaluate

Evaluate how well a job posting matches your background. Paste a JD or URL and get an honest A-F scored assessment with match analysis, compensation research, positioning strategy, and interview prep. Use when someone says 'evaluate this job', 'should I apply', 'how well do I match', 'rate this job', or pastes what…

andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2- · 75 tokens

apply

Help fill out a job application form. Generates personalized answers for every field using your profile and evaluation. Never auto-submits. Use when someone says 'help me apply', 'fill out this application', or 'application for'.

andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2- · 47 tokens