Borrowing it
Nothing to install: this file belongs to drabaioli/cdd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/drabaioli/cdd/main/.claude/commands/cdd-plan.mdgit clone --depth 1 https://github.com/drabaioli/cddWrote 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/commands/drabaioli/cdd/cdd-plan)<a href="https://agentmods.dev/commands/drabaioli/cdd/cdd-plan"><img src="https://agentmods.dev/badge/commands/drabaioli/cdd/cdd-plan/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.
<a href="https://agentmods.dev/commands/drabaioli/cdd/cdd-plan"><img src="https://agentmods.dev/badge/commands/drabaioli/cdd/cdd-plan.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.02674 |
| Opus 5.5 | $0.00000 | $0.01070 |
| Sonnet 5.5 | $0.00000 | $0.00535 |
| Haiku 4.5 | $0.00000 | $0.00267 |
Grade A, and why
cdd-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan a task from its handoff and write the plan file a later /cdd-implement session builds from: /cdd-plan (takes no argument).
This is the first half of the implementation cycle. It runs in the task's feature worktree, and its only artifact is the plan file — it writes no file inside the repo. The second half is a separate, fresh session running /cdd-implement.
Everything you learn here and do not write down is destroyed when this session ends. That is the whole reason the plan file has a schema; follow it.
1. Read the handoff and rebuild context
Derive the task's paths from git — no argument is passed:
repo="$(basename "$(dirname "$(git rev-parse --path-format=absolute --git-common-dir)")")"
branch="$(git rev-parse --abbrev-ref HEAD)"
echo "handoff: ~/.cdd/handoffs/$repo/$branch.md"
echo "plan: ~/.cdd/handoffs/$repo/$branch.plan.md"
Read the handoff. Its ## Requirements section is the done-test for this task: your plan must satisfy every criterion, and you check it against them in step 4. Its ## Notes section lists open questions deferred to you — address them up front rather than mid-plan. Its ## Research section, if present, sets how much research step 3 does and which questions it answers.
Then rebuild context from the repo: the roadmap and the architecture/feature doc indexes, loading only the documents the task touches.
If the plan file already exists, this task has already been planned. Say so, show the existing plan's ## Summary, and ask whether to replan from scratch or hand off to /cdd-implement — do not silently overwrite.
2. Explore
Exploration is a named step, not an implied one. Read the source you will change — whatever the task needs inside the repo. What lies outside it (the web, vendor and library documentation) is the next step's job. Dead ends are expected and are not waste; they are findings.
Record conclusions as you go. After this session ends there is no transcript for the implementing session to consult, so an unrecorded finding is re-derived at full cost or simply lost.
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.
- 6d ago Changed · +50 lines b2b938860391
- 1mo ago Changed c4c52b4e46ef
- 1mo ago Changed · -10 lines b518d241c5d9
- 1mo ago First seen · 116 lines · 0 tokens per session scan A e8615d7dd8f8
cdd-plan is a command published in the GitHub repository drabaioli/cdd (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,674 tokens. 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 2026-09-16.
Other commands, from other repositories
set-tracker
Set the issue tracker for the current project.
ijfw-status
Show IJFW state -- mode, routing, memory, recent activity, codebase index, settings. Use when you want the at-a-glance banner you'd otherwise get at session start.
resume-project
Run resume-project now — Now / Blocked / Next. Not a cheat sheet.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
maggy-init
Interactive wizard that configures Maggy for the user's org, issue tracker, and codebases. Writes /.maggy/config.yaml and ensures deps are installed.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.