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/drag88/claude-dev-framework/plangit clone --depth 1 https://github.com/drag88/claude-dev-frameworkWhat 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 | $0.00023 | $0.00655 |
| Opus 5 | $0.00012 | $0.00328 |
| Sonnet 5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00065 |
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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cdf:plan - Plan Front Door
The moment you have an idea, it is
/cdf:plan. Ground it in your codebase, structure it, persist it as a durable artifact, then hand off to review or execution.
Quick Start
# From a raw idea
/cdf:plan "add semantic re-ranking to the search pipeline"
# From a bug (paste the issue URL or the error text)
/cdf:plan "https://github.com/org/repo/issues/214"
/cdf:plan "psycopg2.OperationalError: connection timed out on the nightly dbt run"
# Name the artifact explicitly
/cdf:plan "multi-tenant billing" --name multi-tenant-billing
When to Use
Use /cdf:plan the moment an idea, bug, or error appears and the work is more than a one-line change. It starts from raw intent — you do not need an existing plan or to have entered plan mode first.
This is the single entry point for planning. It replaces the old "exit plan mode, then run approve" dance: /cdf:plan grounds the work, writes the plan, and routes you onward.
Do not use it for one-line changes (just make them) or for challenging a plan that already exists (use /cdf:plan-review).
Delegation: compound-engineering
This command delegates to the compound-engineering:ce-plan host skill.
Requires: the compound-engineering plugin. If it is not installed, stop and tell the user to install the compound-engineering plugin for their host (install commands are in the README) — do not improvise a replacement flow.
Flow: Invoke the compound-engineering:ce-plan host skill, passing the raw input (idea, bug URL, pasted error, or task description) and the --name value when given as context.
CDF constraints (bind on top of the skill):
- The plan document lands in
docs/plans/(committed — plans compound). - State the scope in one line before research is spent; call out ambiguities the user should correct.
- Ground the plan in the codebase and in
docs/solutions/+.claude/rules/prior learnings. - Hand off when done: recommend
/cdf:plan-review(→compound-engineering:ce-doc-review) for high-stakes plans, otherwise/cdf:implementor/cdf:taskfor execution.
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 · 53 lines · 23 tokens per session scan A 7a42f5a1b59e
plan is a command published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 655 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.