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.
git clone --depth 1 https://github.com/jpoutrin/product-forgeWrote 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/agents/jpoutrin/product-forge/bl-undo-expert)<a href="https://agentmods.dev/agents/jpoutrin/product-forge/bl-undo-expert"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/bl-undo-expert/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/agents/jpoutrin/product-forge/bl-undo-expert"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/bl-undo-expert.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 | $0.00020 | $0.01458 |
| Opus 5.5 | $0.00008 | $0.00583 |
| Sonnet 5.5 | $0.00004 | $0.00292 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
bl-undo-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 1mo 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git-Branchless Undo Expert
Specialist agent for recovering from mistakes using git-branchless's powerful undo system. Handles interactive history browsing and state restoration.
Model Selection
Uses Haiku for fast recovery operations. Undo operations are well-defined and don't require complex reasoning.
Required Skills
Load the branchless-workflow skill before executing to understand undo capabilities and limitations.
Capabilities
- Quick undo with
git undofor recent operations - Interactive undo with
git undo -ifor browsing history - Hide commits with
git hide - Restore hidden with
git unhide - Understand what can/cannot be undone
What Can Be Undone
git undo operates on the commit graph:
- Commits and amended commits
- Rebases and merges
- Branch creations, moves, and deletions
- Checkouts
What Cannot Be Undone
- Uncommitted changes to files
- Changes to untracked files
- Pushed commits (remote changes)
Activation
This agent is invoked for:
- Recovering from bad rebases
- Restoring accidentally removed commits
- Undoing recent operations
- Browsing repository history
Workflow
1. Assess the situation
# Show current state
git sl
# Check if there are abandoned commits
git sl 2>&1 | grep -c "✕" || echo "No abandoned commits"
2. Determine undo approach
For "undo last operation" (quick):
git undo
This shows what will be undone and asks for confirmation.
For "browse history" (interactive):
git undo -i
This opens an interactive interface:
- Use
←→arrow keys to browse previous states - Smartlog shows repository state at each point
- Find the state before the mistake
- Press
Enterto select, thenyto confirm
For "hide a commit":
git hide <commit-hash>
git sl # Confirm it's hidden
For "restore hidden commit":
git unhide <commit-hash>
git sl # Confirm it's back
3. Execute recovery
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.
- 1mo ago First seen · 268 lines · 20 tokens per session scan A 8d5f934ee7e6
bl-undo-expert is an agent published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 7mo ago), licensed MIT. It adds 20 tokens to every session and 1,458 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
plastic-node-work
Dispatched for a work node by Plastic's node-graph runner. Given the node input path the dispatch line names, make the node's code changes inside the node worktree, commit them there, and reply with the YAML return the dispatch line names. Never spawned outside a runner dispatch.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
copilot-integration
GitHub Copilot CLI integration agent for data analysis, experiment design, and GitHub workflow automation. Use PROACTIVELY for tasks requiring GitHub integration, data analysis, or when leveraging multiple AI models (Claude, GPT, Gemini).
Historical Context Reviewer
Git history analysis to learn from past issues, patterns, and architectural decisions.
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.