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 large-redesign-parallel-branch-collision-auditgit 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/large-redesign-parallel-branch-collision-audit)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/large-redesign-parallel-branch-collision-audit"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/large-redesign-parallel-branch-collision-audit/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/large-redesign-parallel-branch-collision-audit"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/large-redesign-parallel-branch-collision-audit.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 | $0.00135 | $0.01880 |
| Opus 5 | $0.00068 | $0.00940 |
| Sonnet 5 | $0.00027 | $0.00376 |
| Haiku 4.5 | $0.00014 | $0.00188 |
Grade A, and why
large-redesign-parallel-branch-collision-audit 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Large-Redesign Parallel-Branch Collision Audit
Problem
You're about to start a large multi-PR redesign that branches from main. The branch is clean, tests are green, the plan is locked. You execute 14 PRs overnight, all merge cleanly to main.
The next day someone asks: "What about the changes on release-uk / feature/whitelabel-X / staging-customer-Y?" — and you discover that long-running branch has 10 unmerged commits, including a11y/safety hotfixes on a file (progress.html, report.html, _base.html) that your redesign has just completely rewritten with the bold-editorial markup.
Now those 10 commits can't be cherry-picked cleanly. The a11y improvements you'd want to keep (innerHTML→DOM migration, button-onclick→href fixes, focus-trap fixes) collide directly with the redesigned markup. Hand-merge required, possibly losing safety improvements if not careful.
The root cause: the redesigner audited main, not main + parallel branches.
Context / Trigger Conditions
Use this audit BEFORE starting work when all of these apply:
- The user requests a multi-PR redesign / migration / restructure (anything that will rewrite ≥3 templates, the base layout, central views, or shared CSS)
- The repo has a multi-branch flow — long-running parallel branches that aren't trivially behind main:
- Client-variant branches (
release-uk,client-acme) - Staging branches (
feature/whitelabel-X) - Pending feature branches with unmerged work
- Client-variant branches (
- The redesign will REPLACE files (not just restyle in-place)
If only restyling in-place (CSS class renames, no structural rewrite), the audit is less critical — git merge can usually combine the changes.
Solution
Pre-flight audit (run BEFORE the implementation plan is locked)
# 1. List all non-stale branches with commits ahead of main
for branch in $(git branch -r --no-merged origin/main 2>/dev/null | grep -v HEAD); do
count=$(git log --oneline origin/main..$branch 2>/dev/null | wc -l | tr -d ' ')
if [ "$count" -gt 0 ]; then
last_activity=$(git log -1 --format="%ar" $branch)
echo "$count commits ahead — $branch (last: $last_activity)"
fi
done
# 2. For each non-stale branch (last activity < 30 days), check file collisions
# with the files your redesign will touch
PLANNED_FILES="webapp/templates/progress.html webapp/templates/report.html webapp/templates/_base.html"
for branch in $(git branch -r --no-merged origin/main | grep -v HEAD); do
hits=$(git log --oneline origin/main..$branch -- $PLANNED_FILES 2>/dev/null | wc -l | tr -d ' ')
if [ "$hits" -gt 0 ]; then
echo "COLLISION RISK: $branch has $hits commits touching planned files:"
git log --oneline origin/main..$branch -- $PLANNED_FILES
fi
done
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 · 136 lines · 135 tokens per session scan A 6fcb70c09701
large-redesign-parallel-branch-collision-audit is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 1,880 once invoked, about $0.0007 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
cloudflare-workers-ci-cd
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.
bump-sdk-version
Bump the FutureSearch SDK version across all files. Use when releasing a new SDK version, updating version numbers, or the user says bump version, release, version bump.
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
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.