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 parallel-session-coedit-via-source-mtime-and-idempotent-rebuildgit 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/parallel-session-coedit-via-source-mtime-and-idempotent-rebuild)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/parallel-session-coedit-via-source-mtime-and-idempotent-rebuild"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/parallel-session-coedit-via-source-mtime-and-idempotent-rebuild/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/parallel-session-coedit-via-source-mtime-and-idempotent-rebuild"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/parallel-session-coedit-via-source-mtime-and-idempotent-rebuild.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 | $0.00142 | $0.02975 |
| Opus 5 | $0.00071 | $0.01488 |
| Sonnet 5 | $0.00028 | $0.00595 |
| Haiku 4.5 | $0.00014 | $0.00298 |
Grade A, and why
parallel-session-coedit-via-source-mtime-and-idempotent-rebuild 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Co-editing a section-assembled deliverable alongside a live parallel session
Problem
The user says: "a parallel session is making active edits on the same file, so please don't delete each other's work — maybe only write on it when the other one is finished." The deliverable is large and shared. The naive readings both fail: serialize (do nothing until they finish — wastes the session, ignores the user's "fan out / go fast") or dive in blindly (and clobber their work, which is exactly what they warned against).
There is a third path that is fast AND safe — but only once you notice the build model: the artifact is assembled from per-item source files, and the assembler is idempotent (reads all sources from disk, regenerates the one output). That changes the collision math entirely.
Context / Trigger conditions
- User warns that another live session / agent is editing the same file; "don't clobber each other"; possibly "only write when the other is finished."
- The deliverable is generated: a build script (
_assemble.py, a bundler, a static-site generator) inlines per-item source files (sections/*.html, partials, slides) into ONE output file. The output is a build artifact, not the source of truth. - You need to make real edits this session without losing concurrent work.
Solution
-
Find the build model FIRST. Never hand-edit the assembled OUTPUT. Locate the assembler and confirm the big file is generated from per-item sources. Edit the source files; the output is regenerated. (If you edit the 2 MB assembled HTML directly, the next rebuild by either session silently overwrites you.)
-
Map hot/cool per item via SOURCE-FILE mtime — this is your real-time ownership signal, no git needed:
stat -f '%Sm %N' -t '%H:%M:%S' sections/*.html # BSD/macOS # or: ls --time-style=+%H:%M:%S -l sections/*.html # GNUFiles touched in the last few minutes = the other session's HOT set; old mtimes = COOL. Re-stat right before each edit batch — the other session moves between cards/items quickly (a broad pass can touch 6+ files in minutes).
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 · 198 lines · 142 tokens per session scan A 477a1edf4910
parallel-session-coedit-via-source-mtime-and-idempotent-rebuild is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed yesterday), licensed MIT. It adds 142 tokens to every session and 2,975 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
vertical-onboarding
Onboarding-and-switching playbook for SMB Product-Builder products. Defines the first-run experience that turns a prospect leaving an incumbent (ServiceTitan/Toast/Mindbody/Shopify/QuickBooks) into an activated user — import-first onboarding, the activation milestone, sample-data fallback, and the time-to-first-value…
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.
sitrep-panel
Keep a live local HTML report updated as you work on a task — a status board, a running "what's happening now" narrative, screenshots, and a newest-first log — served on localhost so the user can watch progress in a browser tab instead of reading the transcript. Use when the user invokes /sitrep-panel, asks for a…
promote
Turn a scratch script into a permanent tool this repo keeps. Use when a check, report, or analysis has proved worth running more than once.
generate-daily-schedule
Use when turning a day's structured inputs — fixed commitments, tasks, and free windows — into a concrete 15-minute schedule. Domain-agnostic; the caller provides all context.
finito
Closes a working session with a coding agent and produces the full closing package: a numbered summary anyone can read, the next steps, what got written down, the real state of the repository including what is left to push, and two blocks the next session resumes from, one to paste after /compact and one to open a…