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.
npx agentmods add skills/clarity-digital-development/tworkflow/dev-workflownpx skills add clarity-digital-development/tworkflow --skill dev-workflowgit clone --depth 1 https://github.com/clarity-digital-development/tworkflowWhat 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 | $0.00106 | $0.01935 |
| Opus 5 | $0.00053 | $0.00967 |
| Sonnet 5 | $0.00021 | $0.00387 |
| Haiku 4.5 | $0.00011 | $0.00194 |
Grade A, and why
dev-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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Workflow
Run a disciplined loop for the change at hand: Plan → Implement → Review → QA → Ship → Retro. (Context — an accurate CLAUDE.md/AGENTS.md — is the standing prerequisite; see the repo's context file.) Determine which phase the user is in from their request and the repo state, and start there — do not force earlier phases if their artifacts already exist.
Core contract for every phase: it consumes a written artifact and produces a written artifact, and the human reads it before the next phase starts.
At every phase boundary: check context usage (invoke the
context-checkpoint skill if installed; otherwise ask the user to run
/context). Past 40%, recommend a compact or clear at this boundary before
entering the next phase.
Templates: prefer the repo's own copies (docs/templates/ or templates/)
if present; otherwise use the copies bundled with this skill at
${CLAUDE_SKILL_DIR}/templates/.
Phase 0 — Triage
Classify the request:
- Trivial (typo, copy, dep bump): skip this workflow, just do it.
- Small (single-file fix): one-paragraph plan inline, then implement.
- Non-trivial (multi-file, behavior change, feature, migration): full loop below.
Phase 1 — Plan
- Copy the PLAN.md template (repo copy, else
${CLAUDE_SKILL_DIR}/templates/PLAN.md) todocs/plans/<YYYY-MM-DD>-<slug>.md. It covers: problem, non-goals, premises, alternatives considered, design (including existing code to reuse), failure modes, UI states (if any), test plan, ordered steps. - Verify every premise against the actual code before presenting the plan; mark each ✅/❌. Library/API claims are premises too — verify them against the installed version's docs, not memory. Do not present a plan with unverified premises.
- Present at least two approaches with tradeoffs and a recommendation.
- Ask the user the scope question explicitly: "What is the smallest version of this that is still useful?" Apply their answer.
- Stop. Wait for explicit approval before writing any code. In Claude Code, suggest the user switch to plan mode (Shift+Tab) for this phase.
What ships with it
5 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.
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.
- 2d ago First seen · 158 lines · 106 tokens per session scan A c899bb8d8870
dev-workflow is a skill published in the GitHub repository clarity-digital-development/tworkflow (46 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 1,935 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
asking-user-questions
Use when composing an askuserquestion round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.
shipping-a-pr
Use when finished work needs to ship as a pull request, or when the ask is about a PR — creating one, bringing it up to date, adding screenshots, watching its checks, or addressing its review comments. Not for reviewing a PR you are not shipping.