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 skills add jpoutrin/product-forge --skill bl-recordgit 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/skills/jpoutrin/product-forge/bl-record)<a href="https://agentmods.dev/skills/jpoutrin/product-forge/bl-record"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/bl-record/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/skills/jpoutrin/product-forge/bl-record"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/bl-record.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 | $0.00015 | $0.00725 |
| Opus 5.5 | $0.00006 | $0.00290 |
| Sonnet 5.5 | $0.00003 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
bl-record 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/bl-record - Git-Branchless Record
Category: Git Workflow
Record staged/unstaged changes as a new commit using git-branchless. Optionally create a branch for the commit.
Usage
/bl-record [-m <message>] [--create-branch]
Options
| Option | Description |
|---|---|
-m <message> |
Commit message (required) |
--create-branch |
Create a branch for PR submission (uses -c flag) |
Examples
# Record with message
/bl-record -m "feat: add user validation"
# Record and create branch for PR
/bl-record -m "fix: handle null input" --create-branch
Execution Instructions
-
Check Prerequisites
- Verify git-branchless is installed
- Verify repository is initialized for branchless
- Check we're in detached HEAD state
-
Stage Changes (if needed)
- Run
git statusto check for changes - If unstaged changes exist, run
git add -Ato stage all
- Run
-
Record the Commit
- If
--create-branchis provided:
Then immediately return to detached HEAD:git branchless record -c -m "<message>"git checkout --detach - Otherwise:
git branchless record -m "<message>"
- If
-
Show Result
- Run
git slto display the updated stack - Confirm the new commit was added
- Run
Flow Examples
User: /bl-record -m "feat: add user model"
Agent: Recording changes...
Staged changes:
A src/models/user.py
M src/models/__init__.py
Running: git branchless record -m "feat: add user model"
◆ abc1234 (main) initial commit
┃
● def5678 feat: add user model ← New commit
Commit recorded successfully.
User: /bl-record -m "fix: validate email" --create-branch
Agent: Recording changes with branch creation...
Staged changes:
M src/validators.py
Running: git branchless record -c -m "fix: validate email"
Branch created: fix-validate-email
Returning to detached HEAD...
Running: git checkout --detach
◆ abc1234 (main) initial commit
┃
● ghi9012 fix: validate email (fix-validate-email) ← New commit with branch
Commit recorded with branch for PR submission.
Use /bl-submit to push the branch.
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 · 119 lines · 15 tokens per session scan A 0faf10f02f3d
bl-record is a skill published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 725 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 skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.