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/notorious-ai/claude-plugins/draft-prgit clone --depth 1 https://github.com/notorious-ai/claude-pluginsWhat 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 | $0.00008 | $0.00814 |
| Opus 5 | $0.00004 | $0.00407 |
| Sonnet 5 | $0.00002 | $0.00163 |
| Haiku 4.5 | $0.00001 | $0.00081 |
Grade A, and why
draft-pr 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 2d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Pull Request
Gather git context and draft an effective pull request using the writing-pull-requests skill. Focus on surfacing the why - intent, constraints, and rationale - that the diff cannot convey.
Step 1: Gather Git Context
Collect information about the current branch:
Branch and commits:
!git branch --show-current && echo "---" && git log --oneline main..HEAD 2>/dev/null | head -15
Files changed:
!git diff main...HEAD --stat 2>/dev/null | tail -15
Step 2: Search for Related Work
Check for related issues and PRs:
Open issues:
!gh issue list --state open --limit 8 2>/dev/null || echo "Could not fetch issues"
Recent PRs:
!gh pr list --state all --limit 5 2>/dev/null || echo "Could not fetch PRs"
Step 3: Surface the Hidden Context
Use probe questions to uncover what the diff cannot show. The writing-pull-requests skill guides what context to capture - focus on:
- Expected outcome - what the change accomplishes (verifiable against the changeset)
- Constraints that shaped the solution - technical, organizational, or timeline limitations
- Designed exclusions - what this change explicitly does not address and why
- Reevaluation triggers - conditions under which to revisit this decision
Ask clarifying questions:
- "What constraint prevented the simpler solution?"
- "What is explicitly out of scope, and why?"
- "Under what conditions should we revisit this approach?"
Use AskUserQuestion if purpose is unclear:
- question: "What problem does this PR solve or what value does it add?"
- header: "Motivation"
- options:
- Bug fix (Corrects incorrect behavior)
- New feature (Adds new capability)
- Improvement (Enhances existing functionality)
- Refactoring (Restructures without behavior change)
Check for linked issues:
- question: "Is there a related issue to link?"
- header: "Issue link"
- options:
- Yes (I'll provide the issue number)
- No issue exists (The PR description will provide context)
- Search again (Help me find related issues)
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.
- 2d ago First seen · 97 lines · 8 tokens per session scan A 134d43817730
draft-pr is a command published in the GitHub repository notorious-ai/claude-plugins (5 stars, last pushed 7d ago), licensed MIT. It adds 8 tokens to every session and 814 once invoked, about $0.0000 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
git
Git operations with intelligent commit messages and workflow optimization.
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.