roadmap-to-workflow

roadmap-to-workflow is a skill for Claude Code from SpaiR/task-pipeline. It costs 36 tokens per session (5,344 once invoked), scanned A, original, MIT.

A workflow driver that turns an approved roadmap into dependency-ordered waves of development work. A roadmap is a planned list of related tasks, and a wave groups tasks that can be planned at the same time.

In plain words
What is it for?
Use it to collect unfinished roadmap items, plan independent items together, then implement, review, and mark off each item one at a time, with optional per-task model choices.
Why use it?
It coordinates parallel planning while keeping implementation and review controlled in the shared codebase, so dependent tasks follow the right order.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the task plugin — 8 skills, 8 agents shipped together

Good fit Use it to collect unfinished roadmap items, plan independent items together, then implement, review, and mark off each item one at a time, with optional per-task model choices.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add SpaiR/task-pipeline
Claude Code
/plugin install task

Made for: Claude Code.

Or install task, the plugin that ships this one along with the rest of its 8 skills, 8 agents.

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 roadmap-to-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/spair/task-pipeline/roadmap-to-workflow.svg)](https://agentmods.dev/skills/spair/task-pipeline/roadmap-to-workflow)
Your own site
<a href="https://agentmods.dev/skills/spair/task-pipeline/roadmap-to-workflow"><img src="https://agentmods.dev/badge/skills/spair/task-pipeline/roadmap-to-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,344 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.05344
Opus 5 $0.00018 $0.02672
Sonnet 5 $0.00007 $0.01069
Haiku 4.5 $0.00004 $0.00534

Measured yesterday against content hash a6462d1b3ecd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

roadmap-to-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 yesterday.

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/roadmap-to-workflow/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drive an approved roadmap through a dynamic Workflow. This skill collects the roadmap's unchecked items, sorts them into dependency-ordered waves, then invokes the plugin-shipped Workflow driver (skills/_lib/roadmap-driver.js, via the Workflow tool's scriptPath) that, within each wave, plans all items in parallel and then implements, reviews, and ticks them off one item at a time in the shared working tree. It does not hand-roll that fan-out itself, and it does not author the Workflow script — the driver is a static file, inspectable at any time, parameterized only through args (Step 2). If the Workflow tool isn't available, it falls back to running items serially by hand, in the same dependency order (Step 2).

Per-item model control. Each roadmap item may carry a **Model:** hint (haiku | sonnet | opus); the driver passes it to that item's implement agent as opts.model, and scales the plan stage down for lightweight items (a haiku-hinted item is planned by sonnet at low effort; everything else by opus). The review agent ignores it — task:code-reviewer pins its own model, so a haiku item never gets a haiku review.

Per-item execution is a three-agent split by default — opus plans (sonnet for haiku-hinted items), the item's model implements and commits, task:code-reviewer reviews and commits its fixes on top; a fourth, cheap driver stage then ticks the roadmap checkbox (Step 2).

This skill is the opt-in for the Workflow tool — reading it and following the Steps is the authorization; there is no magic keyword and no separate confirmation.

Input: $ARGUMENTS — optional. A single positional <roadmap-slug> (or path) to skip the roadmap picker. No flags — item scope is chosen interactively (Step 0).

Format contract: docs/contract.md § Roadmap file format is the single source of truth for item grammar (### - [ ] N., **Dependencies:**, **Model:**); docs/contract.md § task.md format for the artifact each item's plan agent writes.

Step 0: Setup gate, pick roadmap, pick scope

roadmap-to-workflow is not an intake skill — it never runs setup itself (a roadmap can't exist without .task/CLAUDE.md, so an absent one means something upstream is broken).

echo "$CLAUDE_PLUGIN_ROOT"                                 # note this absolute path — pass it as `pluginRoot` in Step 2's args
source "${CLAUDE_PLUGIN_ROOT}/skills/_lib/resolve-ws.sh"   # sourcing runs find_ai_dir → sets AI_DIR
echo "$AI_DIR"                                             # note this one too — pass it as `aiDir` in Step 2's args
[[ -f "$AI_DIR/CLAUDE.md" ]] || echo "CLAUDE.md not found"
bash "${CLAUDE_PLUGIN_ROOT}/skills/validate/validate.sh" all
  • CLAUDE.md not found (the guard above echoes it; validate.sh all also exits 2 with the same message) → hard-stop redirect (do not bootstrap here):

    The project isn't set up yet. Capture something first with /task:to-task, /task:to-plan, /task:to-roadmap, or /task:to-spec — those four set the project up inline. → Next: /task:to-roadmap

  • Any other non-zero exit from validate.shvalidate.sh all checks every artifact, so an error may sit on a task or roadmap unrelated to this run. Mind the timing: at this point the roadmap has not been picked yet (that happens in the Roadmap sub-step below), so do not try to judge here which errors are "yours". Surface every reported error now, block on none of them, and hold the roadmap ones. Once <slug> is resolved below, check the held list: if an error was reported against that file, stop then — "→ Next: fix the reported error in .task/roadmap/<slug>.md, then rerun /task:roadmap-to-workflow <slug>". Errors on any other artifact never block. (The one case where the roadmap is already known at gate time is a positional <roadmap-slug> in $ARGUMENTS; there you may apply the check immediately.) WARN lines never set a non-zero exit; they are informational only.

Read the full file on GitHub · 193 lines

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. yesterday Changed a6462d1b3ecd
  2. 3d ago Changed d5c05f2da0d6
  3. 7d ago First seen · 193 lines · 36 tokens per session scan A e9fda6807eb2

Subscribe to this mod's changes

roadmap-to-workflow is a skill published in the GitHub repository SpaiR/task-pipeline (7 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 5,344 once invoked, about $0.0002 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

batch

Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.

mikestankavich/claude-ship-workflow · 31 tokens

prep

Spec a ticket before it is dispatched. Brainstorms it, decides everything it can recommend an answer for, asks a present human about the little that survives, and leaves the spec, the decisions and anything still open as one ticket comment. No worktree, no branch, no pull request, and the ticket stays where it was.

mikestankavich/claude-ship-workflow · 68 tokens

work

Dispatch a tracker ticket into an isolated worktree and drive it autonomously to an open pull request, then stop for review. Pass interactive to brainstorm the ticket with a human before planning it. Use when asked to work a ticket end-to-end.

mikestankavich/claude-ship-workflow · 53 tokens

daily-working

End-to-end pipeline: pull a task from Redmine by ID, sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension (claude-in-chrome), and keep the Redmine ticket in sync throughout (in-progress…

tms-tungnguyen3/daily_working · 81 tokens

web-drift

Use for the live-website agent-readiness audit, "run the web-drift loop", "audit our websites", "are our sites still readable by an agent", "web drift sweep", "check the public sites", or a scheduled site-audit cadence run. Enumerates every site the consumer declared in WEBDRIFTSITES, probes each over read-only HTTP…

dwarvesf/dwarves-kit · 230 tokens

shipyard-executing-plans

Use when you have a written implementation plan to execute, either in the current session with builder/reviewer agents or in a separate session with review checkpoints. Also use when the user says "build this", "implement this", "execute the plan", "run the plan", or when a plan file has been loaded with independent…

lgbarn/shipyard · 78 tokens