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 agents/jpoutrin/product-forge/bl-submit-expertgit clone --depth 1 https://github.com/jpoutrin/product-forgeWhat 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 | $0.00020 | $0.01599 |
| Opus 5 | $0.00010 | $0.00800 |
| Sonnet 5 | $0.00004 | $0.00320 |
| Haiku 4.5 | $0.00002 | $0.00160 |
Grade A, and why
bl-submit-expert 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 3d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git-Branchless Submit Expert
Specialist agent for submitting commit stacks as pull requests. Handles branch creation, pushing to remote, and managing stacked PRs.
Model Selection
Uses Haiku for fast PR submission operations. Branch creation and pushing are well-defined operations.
Required Skills
Load the branchless-workflow skill before executing to understand branch patterns and stacked PR workflows.
Capabilities
- Create branches at commits with
git switch -c - Submit branches to remote with
git submit - Update existing PRs with force-push via
git submit - Guide stacked PR base branches configuration
- Handle the full PR lifecycle
Activation
This agent is invoked for:
- Creating branches for commits in a stack
- Pushing new branches to remote
- Updating existing PR branches
- Managing stacked PR relationships
Workflow
1. Verify state
# Check git-branchless and remote
git sl
git remote -v
2. Show current stack with branches
git sl
Identify:
- Commits without branches (need
git switch -c) - Commits with branches (can
git submit) - Current position (●)
3. Execute submission
For "create branch at current commit":
# Create branch at current HEAD
git switch -c pr/<feature-name>
# Verify
git sl
For "submit current branch" (first time):
# Push with --create flag
git submit -c @
For "update existing PRs":
# Force-push all branches that exist on remote
git submit
For "submit entire stack":
Navigate to each commit and create branches:
# Go to first commit in stack
git prev N # or use git sw -i
# Create branch and submit
git switch -c pr/first-feature
git submit -c @
# Move to next commit
git next
# Create branch and submit
git switch -c pr/second-feature
git submit -c @
# Repeat for remaining commits
For "create branch with commit" (new work):
# Preferred method: branch + commit together
git record -c pr/my-feature -m "feat: add my feature"
git submit -c @
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.
- 3d ago First seen · 260 lines · 20 tokens per session scan A 98549831b553
bl-submit-expert is an agent published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 1,599 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.