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 commands/alexsds/ade-workflow/plangit clone --depth 1 https://github.com/alexsds/ade-workflowWhat 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 | $0.00017 | $0.00527 |
| Opus 5 | $0.00009 | $0.00264 |
| Sonnet 5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
plan 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.
What it actually says
You are executing the ADE planning workflow. Follow these steps yourself — do NOT spawn a subagent or agent for planning. The planner needs to ask the user questions interactively, which requires staying in the main conversation.
Step 1: Check for project initialization
Check if .ade/ directory exists. If not, run:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/init-project.sh
Step 2: Read project settings
Read .claude/ade.local.md if it exists. Note the commits_style value.
Step 3: Read the planning methodology
Read ${CLAUDE_PLUGIN_ROOT}/skills/ade-planning/SKILL.md and follow it step by step for: $ARGUMENTS
Step 4: Research
Explore the codebase (existing project) or search for similar products (greenfield). Share a summary of your findings with the user.
Step 5: Ask questions interactively
This is critical — ask questions ONE AT A TIME. After each question, STOP and wait for the user's response before asking the next one. Do NOT ask multiple questions at once. Do NOT skip questions. Do NOT write the plan until you've finished asking.
Format every question like this:
What platform should this run on?
a) Web app — works in any browser, easiest to build
b) Mobile-first web app — responsive, installable as PWA
c) Native mobile app — iOS/Android
d) Something else — tell me more
How many questions depends on scope:
- Large (full app): 3-5 questions
- Medium (feature): 1-3 questions
- Small (task/bug): 0-1 questions
After sharing research findings, ask your first question and STOP. Wait for the answer. Then ask the next question and STOP. Repeat until done.
Step 6: Write the plan
Only after all questions are answered, write the plan to .ade/docs/plans/plan-YYYY-MM-DD.md. Structure matches scope per the methodology in the skill.
Step 7: Wait for approval
Tell the user: "Plan written to .ade/docs/plans/plan-YYYY-MM-DD.md. Please review and let me know if you'd like changes. Once approved, use /ade:execute to start implementation."
Do NOT proceed to building until the user explicitly approves.
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.
- yesterday First seen · 56 lines · 17 tokens per session scan A 29b25474ec31
plan is a command published in the GitHub repository alexsds/ade-workflow (1 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 527 once invoked, about $0.0001 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 commands, from other repositories
feature
Orchestrate a complete feature through discovery, spec, implementation, and review.
test
Design or run focused test validation for a task, bug, or diff.
mvp-spec
Research and produce a strict MVP spec with small 1-2 hour tasks and explicit out of scope.
research
Research a technical or product question.
goal
Set a goal and enter the RALPH loop — keep working autonomously until the goal is genuinely done or the user stops you. Use /goal "objective" to start, /goal status to check, /goal complete to finish, /goal clear to stop.
selfloop
Start or control a persistent SIPS loop whose only objective is improving SIPS and the agent operating it through measured, verified iterations.