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 session-handoff-number-collision-with-unmerged-siblinggit 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/session-handoff-number-collision-with-unmerged-sibling)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/session-handoff-number-collision-with-unmerged-sibling"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/session-handoff-number-collision-with-unmerged-sibling/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/session-handoff-number-collision-with-unmerged-sibling"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/session-handoff-number-collision-with-unmerged-sibling.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 | $0.00475 | $0.04317 |
| Opus 5 | $0.00237 | $0.02159 |
| Sonnet 5 | $0.00095 | $0.00863 |
| Haiku 4.5 | $0.00047 | $0.00432 |
Grade A, and why
session-handoff-number-collision-with-unmerged-sibling 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 7d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session-Handoff Number Collision With Unmerged Sibling
Problem
session-handoff Phase 1 Step 2 says "Write handoff doc → docs/handoffs/session_N_handoff.md." The implicit assumption is that you can determine N by inspecting docs/handoffs/ on the current branch. This assumption breaks when a parallel/sibling session ran concurrently in another worktree and its handoff PR hasn't merged into main yet.
Concrete sequence:
- Sibling session ran 2 hours ago in
.claude/worktrees/other/, draftedsession_167_handoff.md, opened PR #690 (still under review). - Sibling session updated MEMORY.md "Recent sessions" with an S167 entry AND appended to sessions_archive.md.
- You fork your worktree off
origin/main— MEMORY.md is local-user-state so you see the sibling's S167 entry, butdocs/handoffs/onorigin/maindoes NOT yet havesession_167_handoff.md(PR pending). - You run
ls docs/handoffs/→ highest is S166b → you pick S167. - You write
docs/handoffs/session_167_handoff.md+session_168_prompt.md. - Both sessions now claim S167. Disk doesn't conflict (different branches). MEMORY.md shows two S167 entries. Future readers can't tell which is canonical.
The collision is silent because:
lsonly sees the current branch's files.git log origin/main -- docs/handoffs/session_167_handoff.mdreturns empty (PR pending).- Pre-commit hooks don't check session-number uniqueness.
- The session-handoff skill itself doesn't tell you to cross-check MEMORY.md.
Context / Trigger Conditions
Activate this check during session-handoff Phase 1 Step 2 (before writing the handoff doc), or during Phase 4 Step 22.a (review-agent factual-accuracy pass), whenever all of:
- You've picked a session number N based on
ls docs/handoffs/. - There's a project-level MEMORY.md or sessions_archive.md that tracks recent sessions.
- The repo is in a "dense parallel-PR" state (multiple worktrees, multiple open handoff PRs in recent days, or a
pr-conflict-from-mid-flight-merges-style skill in the project's skill set).
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.
- 7d ago First seen · 228 lines · 475 tokens per session scan A 254a4b55df71
session-handoff-number-collision-with-unmerged-sibling is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed today), licensed MIT. It adds 475 tokens to every session and 4,317 once invoked, about $0.0024 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 2026-09-05.
Other skills, from other repositories
brain-hydrate
Use when users want to bootstrap the brain with existing project knowledge -- reading ADRs, feature specs, UX docs, commit history, and error patterns to seed institutional memory on a project that already has artifacts on disk. Also use for incremental re-hydration after significant work outside the pipeline.…
session-handoff
Documents the current Claude Code session by writing what changed, what broke, how problems were solved, and what's next into DECISIONS.md, CONTEXT.md, and CLAUDE.md. Then commits everything to git. Use this skill when the user says they are done, wrapping up, finishing, handing off, ending the session, switching…
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.