Borrowing it
Nothing to install: this file belongs to thunder-id/thunderid. 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/thunder-id/thunderid/main/.agent/skills/pr-preflight/SKILL.mdgit clone --depth 1 https://github.com/thunder-id/thunderidWrote 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/thunder-id/thunderid/pr-preflight)<a href="https://agentmods.dev/skills/thunder-id/thunderid/pr-preflight"><img src="https://agentmods.dev/badge/skills/thunder-id/thunderid/pr-preflight/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/thunder-id/thunderid/pr-preflight"><img src="https://agentmods.dev/badge/skills/thunder-id/thunderid/pr-preflight.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 | $0.00034 | $0.00741 |
| Opus 5.5 | $0.00014 | $0.00296 |
| Sonnet 5.5 | $0.00007 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
pr-preflight 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 6d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Preflight
An optional review pass over a finished change. The backend and backend-tests skills already apply these rules while code is written, so run this only when asked. Fix what it finds, then report.
Step 1: Collect the Change
- Base: the merge base with
mainon thethunder-id/thunderidremote, or the release branch the change targets. - Read the full diff against the base, including uncommitted and untracked files.
- Review added lines only. Do not flag or fix existing code the change did not touch.
Step 2: Check Every Added Line
All Files
- No bare short form of the product name (
AGENTS.md, Product Name Rules). - No em dashes or double hyphens in copy, UI strings, i18n locale files, or error messages.
- New source files carry the license header with the current year only, never a range.
- No private keys or real credentials outside test fixtures.
- Nothing outside the task: no unrelated refactoring, no comments on untouched code, no new dependencies, CI, or Makefile changes without approval.
Backend Go
Apply each file of the backend skill to the added code:
-
layout.md: file names, what goes in which file, method order, package comment. -
visibility.md: nothing exported that the package's consumers do not use, exposed interfaces named<Thing>Interface, dependencies and config passed throughInitialize. -
errors.md: error constants inerror_constants.go, codes in ascending order and unused elsewhere,{{param(name)}}placeholders, a description that adds context. -
logging.md: logger on the struct, no logger name constant, no new Info logs for routine operations, no client error or executor error logs, no PII. -
idiom.md: typed constants, header names frominternal/system/constants, no hand-rolled helper the language orinternal/system/utilsalready has, no unaccepted lint suppressions, minimal comments. -
resource.mdandconfig.mdchecklists, when the change adds a resource or a config key. - Query IDs in
store_constants.goare in ascending order with the new one at the end (dbskill).
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.
- 6d ago First seen · 58 lines · 34 tokens per session scan A a344b40b3c1a
pr-preflight is a skill published in the GitHub repository thunder-id/thunderid (594 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 741 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 2026-10-21.
Other skills, from other repositories
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…
gh-pr
Writes clear pull request descriptions from the current branch diff against a base branch. Defaults to main, but supports dev or any other user-specified comparison branch. Use when the user asks for a PR description, pull request summary, or a markdown write-up for changes against a base branch.
gh-rev
Use the gh-rev CLI to maintain a persistent Markdown review ledger for local branches and pull requests. Trigger when the user names gh-rev, asks to save or submit a durable review, inspect or implement existing findings, continue an independent review pass, or adopt branch history into a PR. Use the gh-pr-review…
bmad-loop
Iterate over a list of story keys, executing dev → review → PR → CI → merge for each. Use when the user says "loop these stories [list]" or "run the loop on [story keys]".
conventional-commit
Rules for writing Conventional Commits messages in this project. MUST be invoked every time a commit is created.
code-changes
Workflow for any task that ends in code changes: issue analysis or triage, pull request review comments, features, bug fixes, refactors. Invoke at the start of such a task, before reading or writing code.