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/alexsds/ade-workflow/ade-planningnpx skills add alexsds/ade-workflow --skill ade-planninggit clone --depth 1 https://github.com/alexsds/ade-workflowWrote 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.
[](https://agentmods.dev/skills/alexsds/ade-workflow/ade-planning)<a href="https://agentmods.dev/skills/alexsds/ade-workflow/ade-planning"><img src="https://agentmods.dev/badge/skills/alexsds/ade-workflow/ade-planning.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00115 | $0.02461 |
| Opus 5 | $0.00057 | $0.01230 |
| Sonnet 5 | $0.00023 | $0.00492 |
| Haiku 4.5 | $0.00012 | $0.00246 |
Grade A, and why
ade-planning 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADE Planning
Overview
Planning before building — scaled to the scope of the work. Anthropic's research found that a single error in technical planning cascades through every level of implementation. The planner stays at the deliverable level (what, not how) and lets the Generator figure out implementation.
The planner is interactive. It researches context, asks targeted questions with suggested answers, and writes a plan whose depth matches the scope of the work.
Step 0: Assess Scope
Read the user's request and assess scope. This determines how deep the planning process goes.
Large — Full application, multi-feature project, new product
- Examples: "build me a task management app", "create a SaaS dashboard", "I want to build a marketplace"
- Full planning flow: research → 3-5+ questions → possibly propose approaches → phased plan with user stories
Medium — New feature, significant change, integration
- Examples: "add a notification system", "integrate Stripe payments", "build a settings page"
- Moderate flow: codebase research → 1-3 questions → focused plan with deliverables
Small — Bug fix, task, refactor, minor change
- Examples: "fix the login bug", "refactor the auth module", "our API is too slow", "add dark mode toggle"
- Light flow: quick codebase research → 0-1 questions → short plan with acceptance criteria
The scope determines how many questions to ask, how deep to research, and how detailed the plan is. Don't run a full product planning cycle for a bug fix. Don't write a one-liner plan for a new app.
Step 1: Check Project Context
Before asking any questions:
- Read
.claude/ade.local.mdif it exists — note commit style - Check if
.ade/exists. If not, run${CLAUDE_PLUGIN_ROOT}/scripts/init-project.sh - If
commits_style: jira, ask the user for the Jira ticket number - Check
.ade/docs/plans/for prior plans — understand what has been built before - Check
.ade/docs/archive/for completed plans — understand project history
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.
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.
- 4d ago First seen · 246 lines · 115 tokens per session scan A ddab341047ae
ade-planning is a skill published in the GitHub repository alexsds/ade-workflow (1 stars, last pushed 5mo ago), licensed MIT. It adds 115 tokens to every session and 2,461 once invoked, about $0.0006 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.
Other skills, from other repositories
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).
create-request
Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
codex-code-review
Code review using Codex exec. Use when: PR review, code audit, second opinion on changes. Not for: doc review (use doc-review), security audit (use security-review). Output: severity-grouped findings + merge gate.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
remind
Lightweight model correction with context-aware rule loading. Use when: model forgot a rule, skipped a required step, edited code/docs without running review, needs to re-read CLAUDE.md or rules. Triggers on: 'you forgot', 'remind', 'check rules', 'what did you miss', '你忘了', 'did you skip review', 'why didn't you run…