Borrowing it
Nothing to install: this file belongs to LedgerHQ/ledger-live. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LedgerHQ/ledger-live/develop/.agents/skills/impacting-prs/SKILL.mdgit clone --depth 1 https://github.com/LedgerHQ/ledger-liveWrote 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/ledgerhq/ledger-live/impacting-prs)<a href="https://agentmods.dev/skills/ledgerhq/ledger-live/impacting-prs"><img src="https://agentmods.dev/badge/skills/ledgerhq/ledger-live/impacting-prs/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/ledgerhq/ledger-live/impacting-prs"><img src="https://agentmods.dev/badge/skills/ledgerhq/ledger-live/impacting-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.03308 |
| Opus 5.5 | $0.00036 | $0.01323 |
| Sonnet 5.5 | $0.00018 | $0.00662 |
| Haiku 4.5 | $0.00009 | $0.00331 |
Grade A, and why
impacting-prs 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 2mo 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notify open PRs impacted by an ongoing migration
When: a change is landing (or has landed) that every in-flight PR must follow — a package sunset, an API deprecation, a moved module, a new architectural rule.
Three modes. What gates the ping is whether the replacement is already on develop, not where the removal lives — an author can only act on advice they can commit today. Whether the old path is already gone only sets the severity:
Replacement on develop? |
Old path on develop? |
Mode | What we do |
|---|---|---|---|
| ✅ yes | gone | 🔴 Blocking | review requesting changes on each impacted PR |
| ✅ yes | still there (deprecated, or removed only in a pending PR) | 🟠 Heads-up | comment on each impacted PR |
| ❌ not yet | anything | 🔍 Study | no ping. Report the blast radius to the user, or as one comment on their own migration PR |
The middle row is the common case and the one easy to get wrong: a sunset PR usually only deletes the last legacy alias of something whose successor landed weeks ago. The impacted authors can migrate right now, so ping them — the migration PR being unmerged is a reason to say "landing soon", not a reason to stay silent. Reserve 🔍 study for when the successor genuinely does not exist yet.
Hard rules:
- 🚫 Never post anything before the user has read and approved the drafts.
- 🚫 Never guess the migration pattern. Derive it from the merged work, then have the user confirm it (step 1).
- 🚫 In study mode, never comment on an impacted PR. There is nothing they can do yet: the target API does not exist on
develop, so a ping is noise that ages badly. - ⚖️ Never pick 🔍 study just because the migration PR is open. Check the replacement on
developfirst (step 1); if it resolves there, this is 🟠, and offer the user the choice of pinging now. - 🇬🇧 Everything we post is in English, whatever language the conversation happens in. Being prompted in French is not a reason to write French comments — the PR authors are an international audience.
- 🤖 Every posted message starts with the
🤖icon, so authors can tell at a glance it came from an agent, and so a later run can detect the PR was already informed.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 176 lines · 91 tokens per session scan A 2d08b53ad7fb
impacting-prs is a skill published in the GitHub repository LedgerHQ/ledger-live (624 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 3,308 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…