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 wan-huiyan/agent-traffic-control --skill pr-from-stale-branch-silently-reverts-newer-main-filesgit clone --depth 1 https://github.com/wan-huiyan/agent-traffic-controlWrote 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/wan-huiyan/agent-traffic-control/pr-from-stale-branch-silently-reverts-newer-main-files)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/pr-from-stale-branch-silently-reverts-newer-main-files"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/pr-from-stale-branch-silently-reverts-newer-main-files/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/wan-huiyan/agent-traffic-control/pr-from-stale-branch-silently-reverts-newer-main-files"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/pr-from-stale-branch-silently-reverts-newer-main-files.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 | $0.00387 | $0.04718 |
| Opus 5 | $0.00193 | $0.02359 |
| Sonnet 5 | $0.00077 | $0.00944 |
| Haiku 4.5 | $0.00039 | $0.00472 |
Grade A, and why
pr-from-stale-branch-silently-reverts-newer-main-files 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 12d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A PR from a stale branch can silently revert newer main files (no conflict)
Problem
Your branch's commit records a DELETION of files that are on main. Merging it
applies that deletion, and there is no merge conflict — a removal your own
side committed is not a conflict, it is a change git carries out. The PR looks
"clean", mergeable: MERGEABLE, CI green, and the removals sit in the diff stat
where nobody reads them.
Nobody decides to delete anything. The tree gets that way by accident:
git reset --soft origin/main(or--mixedthengit add -A) run from a branch whose base was old. The POINTER lands on current main; the index still holds the OLD tree; the commit therefore records "delete everything added since" as part of your change.- Committing a stale worktree with
git add -A. Same result — the tree you stage predates main, so everything main gained is staged as removed. - A branch re-created or re-pointed onto a newer base while its working tree stayed old.
What does NOT cause it: simply being behind main
A branch that merely lacks files B/C/D — never had them, never recorded
deleting them — does not delete them on merge. GitHub computes the
merge-base diff (git diff origin/main...HEAD, three dots) and performs a
three-way merge, which preserves B/C/D.
The thing that looks like this trap and is not: git diff origin/main..HEAD
(two dots) compares tip to tip, so every file main gained after your branch
point renders as a deletion your branch appears to be making. That is an
artifact of the wrong command, not a pending revert. Verified: for one PR,
GitHub reported 5 files / 219 insertions / 16 deletions and three-dot matched
exactly, while two-dot reported 4 files / 13 insertions / 22 deletions — a
different file list and deletions that did not exist. Full treatment:
git-diff-2dot-vs-3dot-merge-safety.
Three-dot is not the lax option, either — a branch that genuinely deletes another
session's 418-line file still shows 418 deletions under three-dot. It reports
real removals and drops invented ones.
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.
- 12d ago First seen · 347 lines · 387 tokens per session scan A f7411505fe61
pr-from-stale-branch-silently-reverts-newer-main-files is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed today), licensed MIT. It adds 387 tokens to every session and 4,718 once invoked, about $0.0019 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 2026-08-31.
Other skills, from other repositories
pr-check
PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.
babysit
PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.
git-ops
Git hygiene: clean up merged branches, prune stale remotes, and verify repository state.
misuzu
Respond to PR review comments semi-automatically. Fetches all review threads and comments, splits them into logical units, fixes and commits one unit at a time, then replies and resolves review threads. Use when the user wants to address PR review feedback or respond to review comments.
pr-style
Pull request style guidelines covering title, body, assignee, and label selection. Use when writing or proposing GitHub pull requests, including direct gh pr create invocations outside the /pr skill.
swarm-pi-review
Review a Git working tree or branch with read-only Pi workers. Use standard for bugs, security, regressions, and missing tests; use lean for diff-bound simplification, deletion, reuse, YAGNI, or native replacements. Route one question to ask and broader risk analysis to orchestrate.