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 docs-branch-off-feature-branch-smuggles-codegit 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/docs-branch-off-feature-branch-smuggles-code)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/docs-branch-off-feature-branch-smuggles-code"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/docs-branch-off-feature-branch-smuggles-code/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/docs-branch-off-feature-branch-smuggles-code"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/docs-branch-off-feature-branch-smuggles-code.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 | $0.00454 | $0.04413 |
| Opus 5.5 | $0.00182 | $0.01765 |
| Sonnet 5.5 | $0.00091 | $0.00883 |
| Haiku 4.5 | $0.00045 | $0.00441 |
Grade A, and why
docs-branch-off-feature-branch-smuggles-code 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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs follow-up branch off a feature branch smuggles feature code
Problem
You finish a feature session, the work lives on feat/sN-feature (PR
already open). You want to write a session handoff + the next-session
prompt as a docs-only PR. You run:
git checkout -b docs/sN-handoff-and-sN+1-prompt
# ...write docs, commit, push, gh pr create...
The new branch was created from the current HEAD — which is still
feat/sN-feature's tip. The new docs branch carries the feature
commit AND your docs commits. The PR title is docs(sN+1):.... The
diff includes Dockerfile + src/routes/.py + tests/.py from the
feature work.
If a reviewer squash-merges the "docs" PR, you've just landed the feature code under a docs title — bypassing the planned merge order, potentially auto-deploying if cloudbuild.yaml triggers on main push, and definitely confusing anyone who reads the git log later.
Context / Trigger Conditions
There are three variants. A and B differ by whether the feature PR is still open or was already squash-merged; C is the case where the branch is not yours at all:
Variant A — Feature PR still open (silent code smuggling)
You are in this trap when all of these hold:
-
End-of-session handoff workflow. You're wrapping up a session that produced code changes (already on a feature branch with an open PR) and you're about to write the handoff doc + next-session prompt as a separate PR.
-
You created the docs branch via
git checkout -bfrom inside the feature worktree without specifying an explicit base. Most common variant: you're sitting onfeat/sN-featureand rungit checkout -b docs/sN-handoff— the new branch points atfeat/sN-feature's tip. -
gh pr diff --name-onlyshows non-docs/files. Code, Dockerfile, tests, lock files, generated artefacts. The docs PR title says it ships docs but the diff contradicts. -
git log origin/main..HEADshows more commits than you authored this session for docs. The extra commit(s) are from your own feature work, carried over by the implicit base.
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 Changed · +36 lines c4d55ac3ff8c
- 1mo ago First seen · 377 lines · 454 tokens per session scan A d756add9dc95
docs-branch-off-feature-branch-smuggles-code is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 1mo ago), licensed MIT. It adds 454 tokens to every session and 4,413 once invoked, about $0.0018 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 2026-08-31.
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.
deploy-landed
A deployment verification procedure that checks whether the intended code revision is actually running, its environment settings are present, and the product works. A deployment is the process of putting new software on a server or hosting platform.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…
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.
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.
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.