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-implement.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-implement)<a href="https://agentmods.dev/commands/drabaioli/cdd/cdd-implement"><img src="https://agentmods.dev/badge/commands/drabaioli/cdd/cdd-implement/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-implement"><img src="https://agentmods.dev/badge/commands/drabaioli/cdd/cdd-implement.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 | $0.01071 |
| Opus 5.5 | $0.00000 | $0.00428 |
| Sonnet 5.5 | $0.00000 | $0.00214 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
cdd-implement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement the task from its approved plan file, update the docs, and commit locally: /cdd-implement (takes no argument).
This is the second half of the implementation cycle, run in a fresh context in the same feature worktree that /cdd-plan ran in. Its input is the plan file. That file exists because a human approved it at checkpoint 3, which is why this session needs no gate of its own — and why it must not quietly decide something the plan does not say.
1. Read the plan
Derive the task's paths from git — no argument is passed:
repo="$(basename "$(dirname "$(git rev-parse --path-format=absolute --git-common-dir)")")"
branch="$(git rev-parse --abbrev-ref HEAD)"
echo "plan: ~/.cdd/handoffs/$repo/$branch.plan.md"
echo "handoff: ~/.cdd/handoffs/$repo/$branch.md"
Read the plan first, in full. Its ## Summary is your orientation; the rest is the detail.
Then read the handoff, for its ## Requirements — those acceptance criteria are the done-test, and they survived both windows precisely so that a plan which misread the intent is still caught here.
The plan's sections carry different weights, by design:
## File mapnames the files to open and the conclusion already reached about each. Re-read those files — the plan cites repo facts rather than copying them because they are cheap for you to re-derive.## External findingsis quoted verbatim because it cannot be re-derived here. Trust it; do not go re-run the searches. Each finding names what it is for — act on its disposition, and check a "to verify" finding the way## Verificationsays.## Dead endsrecords approaches already tried and rejected. Do not re-explore them.## Open questions resolvedrecords what the handoff deferred and what was agreed. Those answers are settled; do not reopen them unilaterally.
2. Deviation rule: stop and report, never improvise
If reality contradicts the plan, stop and report to the human. Do not silently pick a different approach, and do not fall back to re-deriving the task from the handoff. The plan was the thing that was approved; departing from it unsupervised discards the checkpoint.
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 0edf6fbb9d1f
- 1mo ago Changed 497d4e06dca6
- 1mo ago First seen · 69 lines · 0 tokens per session scan A 8d569b00196b
cdd-implement 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 1,071 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
undo-commit
Soft-undo the last commit. Restores its changes as staged, leaves working tree intact. Refuses if HEAD is already pushed to a tracked remote.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.
simplify-transform
Apply verified simplifications with user approval. Part of simplify- family.
fix-tests-execute
Phase 2 of fixing-tests: Fix Execution - investigate, classify, fix, verify, and commit each work item.
verify
Run verification commands and confirm output before making success claims. Use before committing, creating PRs, or claiming work is complete. Evidence before assertions, ALWAYS.