What is multi-step-workflow?

A standard operating procedure for handling larger engineering tasks through planning, task tracking, approval gates, and audit-focused private storage. It uses a shorter path for tasks with fewer than three steps and a longer path for more complex work.

Breaking down engineering work, recording plans in task-tracker.js and implementation_plan.md, identifying independent tasks, and generating research and design artifacts. It is intended for multi-step changes that need a traceable process.

It reduces missed planning steps and makes complex work easier to review before changes are made. It also requires approval before the execution phase of the longer workflow.

multi-step-workflow — Skill for Claude Code and Codex by chyern

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.

Any agent

npx skills add chyern/Agent-Skills --skill multi-step-workflow

Clone the repo

git clone --depth 1 https://github.com/chyern/Agent-Skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chyern/agent-skills/multi-step-workflow/github.svg)](https://agentmods.dev/skills/chyern/agent-skills/multi-step-workflow)

Your own site

<a href="https://agentmods.dev/skills/chyern/agent-skills/multi-step-workflow"><img src="https://agentmods.dev/badge/skills/chyern/agent-skills/multi-step-workflow/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chyern/agent-skills/multi-step-workflow"><img src="https://agentmods.dev/badge/skills/chyern/agent-skills/multi-step-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 950 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00027	$0.00950
Opus 5.5	$0.00011	$0.00380
Sonnet 5.5	$0.00005	$0.00190
Haiku 4.5	$0.00003	$0.00095

Measured 1mo ago against content hash b0becc6aeae5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

multi-step-workflow 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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/approve.js, scripts/context-snapshot.js, scripts/path-resolver.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

multi-step-workflow/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Standard Task SOP (High-Trust Edition)

Follow this adaptive workflow to ensure task reliability and professional-grade execution.

Phase 0: Triage & Analyze

Analyze: Assess task scope within the workspace.
Threshold Check:
- Simple Path: < 3 steps. Direct execution.
- Standard Path: >= 3 steps. Follow Path B.

[Path A] Simple Path

Confirm intent -> Execute -> Report. DONE.

[Path B] Standard Path (Machine-Gated)

For complex engineering, act as a Manager and ensure all workers are Sandboxed.

Phase 1: Confirm

Summarize your understanding and align on the objective.

Phase 2: Create Plan

Decompose: Register steps in task-tracker.js.
Parallelize: Identify independent sub-tasks for delegation.
Draft Plan: Create implementation_plan.md. Be explicit about worker scope.

Phase 3: Obtain Approval (Planning Mode - THE GATE)

[!IMPORTANT] YOU ARE IN PLANNING MODE.

Present plan. MUST YIELD and wait for user approval.

GATING: Once approved, YOU MUST RUN: node scripts/approve.js "<task>"

DO NOT modify any files until this symbolic gate script is run.

Phase 4: Execute (Autonomous Loop)

[!TIP] YOU ARE IN AUTONOMOUS LOOP.

Sequential by Default: Execute the plan steps sequentially yourself.

Configurable Sub-agents: BEFORE parallelizing work:

Check Configuration: Run openclaw config get skills.entries.multi-step-workflow.config.

Initialization: If config is empty or errors, run openclaw config set skills.entries.multi-step-workflow.config '{"useSubAgents": false, "maxSubAgents": 3, "useSnapshots": false}' --strict-json.

Modify Configuration (if needed): Run openclaw config set skills.entries.multi-step-workflow.config.<key> <value> --strict-json.

Defaults (if missing): useSubAgents: false, maxSubAgents: 3.

If useSubAgents is false, DO NOT use spawn.

If useSubAgents is true, you may use spawn (limit: maxSubAgents).

RESTRICTION: Do NOT use spawn for arbitrary OS commands or network scanning.

Progress: Mark steps done. Report each step and IMMEDIATELY move to the next.

Context Preservation (Anti-Amnesia):

Check useSnapshots: Run openclaw config get skills.entries.multi-step-workflow.config (Default: false).

Execute (Only if useSnapshots is true): If you extract a crucial finding OR if the task is taking many turns: node scripts/context-snapshot.js save "<task>" "<findings>" "<pending>" ["<last_error_log>"]

Self-Healing: If you suspect context compaction, run node scripts/context-snapshot.js load to recover.

Read the full file on GitHub · 76 lines

Files

What ships with it

7 files 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.

1mo ago First seen · 76 lines · 27 tokens per session scan A b0becc6aeae5

Subscribe to this mod's changes

multi-step-workflow is a skill published in the GitHub repository chyern/Agent-Skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 950 once invoked, about $0.0001 per session on Opus 5.5. 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.

Planning Project management

story-readiness

Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.

Donchitos/Claude-Code-Game-Studios · 48 tokens

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

qa-project-bootstrap

Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…

petrkindlmann/qa-skills · 124 tokens

remove

Remove a deployed framework or addon from the current workspace.

jmagly/aiwg · 12 tokens